CN112560548A - Method and apparatus for outputting information - Google Patents
Method and apparatus for outputting informationDownload PDFInfo
- Publication number
- CN112560548A CN112560548ACN201910907185.7ACN201910907185ACN112560548ACN 112560548 ACN112560548 ACN 112560548ACN 201910907185 ACN201910907185 ACN 201910907185ACN 112560548 ACN112560548 ACN 112560548A
- Authority
- CN
- China
- Prior art keywords
- ground
- point cloud
- threshold
- determining
- plane
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for outputting information.
Background
At present, laser radar ranging is widely applied to the fields of automatic driving, auxiliary driving and the like due to the excellent characteristics and strong adaptability to the external environment. In an application scenario of data acquired by a laser radar, many parameters are often required to be adjusted. Relying on manual adjustment of these parameters is often time consuming and labor intensive.
Disclosure of Invention
The embodiment of the application provides a method and a device for outputting information.
In a first aspect, an embodiment of the present application provides a method for outputting information, including: determining a predicted ground according to point cloud data acquired by a vehicle in the driving process; determining a plurality of ground threshold values according to a preset ground threshold value range; for each ground threshold, determining ground point clouds according to the predicted ground and the ground threshold, and identifying obstacles in the point clouds except the ground point clouds in the point cloud data to determine the number of the obstacles; and determining and outputting the target ground threshold according to the obtained plurality of quantities.
In some embodiments, the determining a plurality of ground thresholds according to a preset ground threshold value range includes: and selecting a plurality of points in the value range of the ground threshold value at preset distance intervals as a plurality of ground threshold values.
In some embodiments, the performing obstacle identification on point clouds in the point cloud data except for the ground point cloud and determining the number of obstacles includes: carrying out obstacle identification on point clouds except the ground point cloud in the point cloud data, and determining the size of an obstacle; and determining the number of obstacles with the height smaller than a preset height threshold value according to the size of the obstacles.
In some embodiments, the determining and outputting the target ground threshold according to the obtained plurality of quantities includes: determining a quantity-ground threshold curve according to the plurality of quantities and the ground threshold corresponding to each quantity; determining the slope of the curve at each ground threshold, and determining the target ground threshold according to each slope.
In some embodiments, the determining the target ground threshold according to the slopes includes: determining the maximum value of the absolute values of the slopes; and taking the ground threshold corresponding to the maximum value as a target ground threshold.
In some embodiments, the determining the predicted ground surface according to the point cloud data collected during the driving process of the vehicle includes: determining estimated ground point cloud in the point cloud data; dividing a first three-dimensional space where the estimated ground point cloud is located into a plurality of second three-dimensional spaces; performing ground estimation on the estimated ground point clouds in the second three-dimensional spaces to obtain a plurality of ground sub-planes; generating the predicted terrain based on the plurality of terrain sub-planes.
In some embodiments, the determining the estimated ground point cloud from the point cloud data includes: and taking the point cloud points in the distance estimation ground preset height range in the point cloud data as the estimation ground point cloud.
In some embodiments, the dividing the first stereo space in which the estimated ground point cloud is located into a plurality of second stereo spaces includes: dividing the estimated ground into a plurality of grids; and dividing the first three-dimensional space based on a plurality of grids to obtain a plurality of second three-dimensional spaces.
In some embodiments, the performing ground estimation on the estimated ground point clouds in the second stereo spaces to obtain a plurality of ground sub-planes includes: fitting estimated ground point cloud points in a plurality of second three-dimensional spaces to obtain a plurality of first planes; for each first plane, the following fitting steps are performed: selecting estimated ground point cloud points with the distance from the first plane being smaller than a first distance threshold value from a second three-dimensional space corresponding to the first plane as candidate point cloud points; fitting a second plane by using the candidate cloud points; determining whether the second plane is stable; and if the second plane is stable, taking the second plane as a ground sub-plane.
In some embodiments, the above performing ground estimation on the estimated ground point cloud points in the second stereo spaces to obtain a plurality of ground sub-planes further includes: in response to determining that the second plane is unstable, replacing the first plane with the second plane and continuing to perform the fitting step.
In some embodiments, the fitting a plurality of first planes based on the estimated ground point clouds in the second stereo spaces includes: for each second three-dimensional space, sampling estimated ground point cloud points in the second three-dimensional space to obtain sampling point cloud points; and fitting the cloud points of the sampling points to a first plane.
In some embodiments, the sampling the estimated ground point cloud points in the second stereo space includes: dividing the second three-dimensional space into a plurality of third three-dimensional spaces; and sampling the estimated ground point cloud points in each third stereo space.
In some embodiments, the determining whether the second plane is stable includes: determining whether the sum of the distances from the estimated ground point cloud points in the second three-dimensional space to the second plane is smaller than a second distance threshold or not in response to the fact that the execution times of the fitting step is smaller than a preset time threshold; if the sum of the distances is smaller than the second distance threshold, determining that the second plane is stable; and if the sum of the distances is not less than the second distance threshold, determining that the second plane is unstable.
In some embodiments, the above method further comprises: and determining that the estimated ground point cloud points do not exist in the second stereo space in response to the execution times of the fitting step not being less than the time threshold.
In some embodiments, the above method further comprises: and determining that the estimated ground point cloud points do not exist in the second three-dimensional space in response to that the execution times of the fitting step is not less than a preset time threshold and the angle between the second plane and the ground is greater than an angle threshold.
In a second aspect, an embodiment of the present application provides an apparatus for outputting information, including: a predicted ground determination unit configured to determine a predicted ground from point cloud data collected during a driving of the vehicle; the ground threshold value determining unit is configured to determine a plurality of ground threshold values according to a preset ground threshold value range; an obstacle number determination unit configured to determine, for each ground threshold, a ground point cloud from the predicted ground and the ground threshold, and perform obstacle identification on point clouds other than the ground point cloud in the point cloud data to determine the number of obstacles; and the target ground threshold value determining unit is configured to determine and output a target ground threshold value according to the obtained plurality of quantities.
In some embodiments, the above-mentioned ground threshold determination unit is further configured to: and selecting a plurality of points in the value range of the ground threshold value at preset distance intervals as a plurality of ground threshold values.
In some embodiments, the above-mentioned number of obstacles determination unit is further configured to: carrying out obstacle identification on point clouds except the ground point cloud in the point cloud data, and determining the size of an obstacle; and determining the number of obstacles with the height smaller than a preset height threshold value according to the size of the obstacles.
In some embodiments, the target ground threshold determination unit is further configured to: determining a quantity-ground threshold curve according to the plurality of quantities and the ground threshold corresponding to each quantity; determining the slope of the curve at each ground threshold, and determining the target ground threshold according to each slope.
In some embodiments, the target ground threshold determination unit is further configured to: determining the maximum value of the absolute values of the slopes; and taking the ground threshold corresponding to the maximum value as a target ground threshold.
In some embodiments, the above-described prediction ground determination unit includes: a point cloud determination module configured to determine an estimated ground point cloud from the point cloud data; the space dividing module is configured to divide a first stereo space where the estimated ground point cloud is located into a plurality of second stereo spaces; the ground estimation module is configured to perform ground estimation on the estimated ground point clouds in the second stereo spaces to obtain a plurality of ground sub-planes; a ground generation module configured to generate the predicted ground based on the plurality of ground sub-planes.
In some embodiments, the point cloud determination module is further configured to: and taking the point cloud points in the distance estimation ground preset height range in the point cloud data as the estimation ground point cloud.
In some embodiments, the spatial division module is further configured to: dividing the estimated ground into a plurality of grids; and dividing the first three-dimensional space based on a plurality of grids to obtain a plurality of second three-dimensional spaces.
In some embodiments, the surface estimation module is further configured to: fitting estimated ground point cloud points in a plurality of second three-dimensional spaces to obtain a plurality of first planes; for each first plane, the following fitting steps are performed: selecting estimated ground point cloud points with the distance from the first plane being smaller than a first distance threshold value from a second three-dimensional space corresponding to the first plane as candidate point cloud points; fitting a second plane by using the candidate cloud points; determining whether the second plane is stable; and if the second plane is stable, taking the second plane as a ground sub-plane.
In some embodiments, the surface estimation module is further configured to: and in response to determining that the second plane is unstable, replacing the first plane with the second plane and continuing to perform the fitting step.
In some embodiments, the surface estimation module is further configured to: for each second three-dimensional space, sampling estimated ground point cloud points in the second three-dimensional space to obtain sampling point cloud points; and fitting the cloud points of the sampling points to a first plane.
In some embodiments, the surface estimation module is further configured to: dividing the second three-dimensional space into a plurality of third three-dimensional spaces; and sampling the estimated ground point cloud points in each third stereo space.
In some embodiments, the surface estimation module is further configured to: determining whether the sum of the distances from the estimated ground point cloud points in the second three-dimensional space to the second plane is smaller than a second distance threshold or not in response to the fact that the execution times of the fitting step is smaller than a preset time threshold; if the sum of the distances is smaller than the second distance threshold, determining that the second plane is stable; and if the sum of the distances is not less than the second distance threshold, determining that the second plane is unstable.
In some embodiments, the above-mentioned prediction ground determining unit further comprises: and the first determining module is configured to determine that the estimated ground point cloud points do not exist in the second stereo space in response to the number of times of executing the fitting step being not less than the number threshold.
In some embodiments, the above-mentioned prediction ground determining unit further comprises: and the second determining module is configured to determine that the estimated ground point cloud points do not exist in the second three-dimensional space in response to the fact that the execution times of the fitting step are not less than a preset time threshold and the angle between the second plane and the ground is greater than an angle threshold.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device, on which one or more programs are stored, which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any of the embodiments of the first aspect.
In a fourth aspect, the present application provides a computer-readable medium, on which a computer program is stored, which when executed by a processor implements the method as described in any one of the embodiments of the first aspect.
According to the method and the device for outputting the information, which are provided by the embodiment of the application, the predicted ground can be determined according to the point cloud data collected by the vehicle in the driving process. And determining a plurality of ground threshold values according to a preset ground threshold value range. Then, for each ground threshold, determining ground point clouds according to the predicted ground and the ground threshold, and identifying obstacles in the point cloud data except for the point clouds on the ground, thereby determining the number of the obstacles. And finally, determining and outputting the target ground threshold according to the obtained plurality of quantities. According to the method, the ground threshold value in the point cloud data processing process can be determined according to the number of the obstacles, so that manual adjustment is not needed, and automatic adjustment of the ground threshold value is achieved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram for one embodiment of a method for outputting information, in accordance with the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for outputting information according to the present application;
FIG. 4 is a flow diagram of one embodiment of determining a predicted terrain in a method for outputting information according to the present application;
FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for outputting information according to the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing an electronic device according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows anexemplary system architecture 100 to which embodiments of the present method for outputting information or apparatus for outputting information may be applied.
As shown in fig. 1, thesystem architecture 100 may includeautonomous vehicles network 104, and aserver 105. Network 104 is used to provide a medium for communication links betweenautonomous vehicles server 105.Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
Various sensors, such as laser radars, may be mounted on theautonomous vehicles autonomous vehicles autonomous vehicles autonomous vehicles
Theserver 105 may be a server that provides various services, such as a background server that processes point cloud data collected by thevehicles vehicles
Theserver 105 may be hardware or software. When theserver 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When theserver 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the method for outputting information provided in the embodiment of the present application may be executed by thevehicles server 105. Accordingly, the means for outputting information may be provided in thevehicles server 105.
It should be understood that the number of vehicles, networks, and servers in FIG. 1 is merely illustrative. There may be any number of vehicles, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, aflow 200 of one embodiment of a method for outputting information in accordance with the present application is shown. The method for outputting information of the embodiment comprises the following steps:
with continued reference to FIG. 2, aflow 200 of one embodiment of a method for outputting information in accordance with the present application is shown. The method for outputting information of the embodiment comprises the following steps:
In the present embodiment, an executing subject of the method for outputting information (for example, thevehicles server 105 shown in fig. 1) may acquire point cloud data acquired by the vehicle during driving by a wired connection manner or a wireless connection manner. The point cloud data may include information about a plurality of point cloud points, such as coordinates, reflection intensity, and the like.
The vehicle can be various vehicles, and a laser radar sensor can be mounted on the vehicle and used for collecting point cloud data of the vehicle in the driving process. After the execution subject obtains the point cloud data, the execution subject can analyze the point cloud data to determine the predicted ground. Specifically, the execution main body may determine point cloud points in a certain range above and below the estimated ground as the estimated ground point cloud according to the estimated ground point set in advance, and then determine the predicted ground according to the estimated ground point cloud. For example, the execution subject may divide the estimated ground point cloud into a plurality of stereo meshes, calculate a central point of each stereo mesh, then connect the central points of the meshes into a surface, and finally use the obtained surface as the predicted ground.
In this embodiment, the execution subject may obtain a preset ground threshold value range, and the ground threshold value range may be determined according to values of a plurality of preset ground thresholds. Each ground threshold may be set by a technician based on his own experience. The execution main body can interval preset distance values in the ground threshold value range to obtain a plurality of ground threshold values. For example, the range of the ground threshold is 0.5m to 1.5m, and the execution subject can take values at intervals of 0.1m, so that a plurality of ground thresholds, which are 0.5m, 0.6m, and 0.7m … … 1.5.5 m, can be obtained. Alternatively, the execution subject may randomly select a plurality of ground thresholds from the above-mentioned ground threshold value range.
In some optional implementations of the present embodiment, the performing agent may determine the plurality of ground thresholds by the following steps not shown in fig. 2: and selecting a plurality of points in the value range of the ground threshold value at preset distance intervals as a plurality of ground threshold values.
In this implementation, the execution subject may select a plurality of points in the range of the ground threshold value as a plurality of ground threshold values at preset distance intervals. Specifically, the above-mentioned ground threshold value range may be divided by the distance interval.
After determining the plurality of ground thresholds, the executive may process for each ground threshold. Specifically, the executing agent may determine the ground point cloud according to the predicted ground and the threshold values of each ground. For example, the performing agent may use, as the ground point cloud, cloud points of points above the predicted ground and at a distance from the predicted ground that is less than or equal to a ground threshold. Then, the executing subject may perform obstacle identification on the point clouds in the point cloud data except for the ground point cloud to determine the number of obstacles contained therein.
The executing subject may recognize an obstacle included in each point cloud frame in the point cloud data using a pre-trained obstacle recognition model or an obstacle recognition algorithm (e.g., a point cloud segmentation algorithm, a feature extraction algorithm, etc.), and may also recognize an obstacle included in each image frame in the image data. Specifically, the executing body may input each point cloud frame of the point cloud data or each image frame of the image data from the input side of the obstacle recognition model, and the output side of the obstacle recognition model may obtain the recognized obstacle.
In some optional implementations of the present embodiment, when performing obstacle identification, the executing body may perform the following steps not shown in fig. 2: carrying out obstacle identification on point clouds except the ground point cloud in the point cloud data, and determining the size of an obstacle; and determining the number of obstacles with the height smaller than a preset height threshold value according to the size of the obstacles.
In this implementation, the execution main body can determine the size of the obstacle after recognizing the obstacle. Specifically, the executing body may determine the size of the obstacle according to the coordinates of cloud points of each point corresponding to the obstacle. The executive may then determine the number of obstacles having a height less than a preset height threshold. For higher obstacles, a change in the ground threshold generally has no effect on the identification of the obstacle. For shorter obstacles, if the ground threshold is set too high, it may be missed and the resulting number of obstacles is small. If the ground threshold is set too low, then smaller sized obstacles may be detected, resulting in a greater number of obstacles. That is, the ground threshold value has a large influence on the detection result of an obstacle having a small size, and has a small influence on the detection result of a large obstacle. Therefore, in the implementation, when counting the number of obstacles, only the number of obstacles with the height smaller than the preset height threshold value can be counted.
And step 204, determining and outputting a target ground threshold according to the obtained plurality of quantities.
In this embodiment, as the ground threshold increases, more and more point cloud points are considered as ground point clouds, and the number of point cloud points in the obstacle point cloud decreases. Accordingly, the number of obstacles detected by the execution subject also becomes smaller. That is, as the ground threshold increases, the number of missed obstacles increases, and the missed detection rate increases. The number of the obstacles detected by mistake is less and less, and the false detection rate is less and less. Theoretically, the intersection point of the undetected rate curve and the false rate curve is the most appropriate ground threshold value. Meanwhile, this intersection point is also the point at which the number of obstacles decreases the fastest. Therefore, the executing body can determine the point where the number of the obstacles is reduced the fastest according to the obtained plurality of numbers, and the value of the ground threshold corresponding to the point is taken as the target ground threshold. And outputs the target ground threshold.
In some optional implementations of the present embodiment, the performing agent may determine the target ground threshold by the following steps not shown in fig. 2: determining a quantity-ground threshold curve according to the plurality of quantities and the ground threshold corresponding to each quantity; determining the slope of the curve at each ground threshold, and determining the target ground threshold according to each slope.
In this implementation, the execution subject may use the ground threshold as the X axis and the number of obstacles as the Y axis according to the number of obstacles corresponding to each ground threshold, and make a curve of the number-the ground threshold. The executive may then determine the slope of the curve at each ground threshold according to the equation for the curve. The slope here may refer to the rate of change of the number of obstacles. The execution subject may determine the target ground threshold based on the obtained slopes. For example, the execution subject may take the ground threshold at which the absolute value of the slope is maximum as the target ground threshold. Alternatively, the execution subject may calculate a mean value of the slopes, and then use a ground threshold corresponding to the mean value as the target ground threshold.
In some optional implementations of the present embodiment, the performing agent may determine the target ground threshold by the following steps not shown in fig. 2: determining the maximum value of the absolute values of the slopes; and taking the ground threshold corresponding to the maximum value as a target ground threshold.
In this implementation, the execution body may determine a maximum value among absolute values of the slopes; and taking the ground threshold corresponding to the maximum value as a target ground threshold.
With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method for outputting information according to the present embodiment. In the application scenario of fig. 3, theautonomous vehicle 301 collects point cloud data through a lidar sensor installed therein during driving, and sends the point cloud data to theserver 302. Theserver 302 performs the processing ofsteps 201 to 204 on the point cloud data, determines a target ground threshold, and sends the target ground threshold to theautonomous vehicle 301.Autonomous vehicle 301 may perform real-time obstacle recognition during travel based on the target ground threshold described above.
According to the method for outputting the information, which is provided by the embodiment of the application, the predicted ground can be determined according to the point cloud data acquired by the vehicle in the driving process. And determining a plurality of ground threshold values according to a preset ground threshold value range. Then, for each ground threshold, determining ground point clouds according to the predicted ground and the ground threshold, and identifying obstacles in the point cloud data except for the point clouds on the ground, thereby determining the number of the obstacles. And finally, determining and outputting the target ground threshold according to the obtained plurality of quantities. According to the method, the ground threshold value in the point cloud data processing process can be determined according to the number of the obstacles, so that manual adjustment is not needed, and automatic adjustment of the ground threshold value is achieved.
With continued reference to fig. 4, aflow 400 of one embodiment of determining a predicted terrain in a method for outputting information according to the present application is shown. It is understood that the execution main body of the present embodiment may be the same as or different from the execution main body of the embodiment shown in fig. 2. When the execution subject of the present embodiment is different from the execution subject of the embodiment shown in fig. 2, the execution subject of the present embodiment may transmit the determined prediction ground to the execution subject of the embodiment shown in fig. 2. As shown in fig. 4, the predicted terrain may be determined in this embodiment by:
In this embodiment, the execution subject may select the estimated ground point cloud from the point cloud data. Specifically, the execution subject may determine the estimated ground point cloud according to the heights of the cloud points of the points in the point cloud data. For example, the executing subject may determine a point cloud point with the lowest height, and then use a point cloud point with a height difference value between the height of each point cloud point and the point cloud point being less than a preset threshold value as the estimated ground point cloud.
In some optional implementations of this embodiment, the performing agent may determine the estimated ground point cloud by the following steps not shown in fig. 4: and taking point cloud points in the point cloud data within a preset height range of the estimated ground as the estimated ground point cloud.
In this implementation, the execution subject may first obtain the estimated ground. The estimated ground can be preset by a technician and sent to the execution main body, or the execution main body can be determined according to the position of the laser radar sensor. After determining the estimated ground, the execution subject may use point cloud points within a preset height range from the estimated ground in the point cloud data as the estimated ground point cloud.
After determining the estimated ground point cloud, the executing subject may divide a first stereo space in which the estimated ground point cloud is located into a plurality of second stereo spaces. It can be understood that the estimated ground point cloud is a three-dimensional space, the bottom surface of the three-dimensional space is a section of the point cloud data to the ground, and the height is a preset height. The execution body may divide the first stereoscopic space into a plurality of second stereoscopic spaces in various forms.
In some optional implementations of this embodiment, the execution body may divide the first stereoscopic space into a plurality of second stereoscopic spaces by the following steps not shown in fig. 4: dividing the estimated ground into a plurality of grids; and segmenting the first three-dimensional space based on the grids to obtain a plurality of second three-dimensional spaces.
In this implementation, the execution main body may perform mesh division on the estimated ground to obtain a plurality of meshes. Then, the execution main body may use each mesh as a bottom surface and a preset height as a height, so as to obtain a plurality of second three-dimensional spaces. In practical application, in order to reduce the calculation amount, the execution subject may also perform projection processing on the point cloud data to obtain a projection ground. The projected terrain is then gridded.
And 403, performing ground estimation on the estimated ground point clouds in the second three-dimensional spaces to obtain a plurality of ground sub-planes.
After obtaining the plurality of second stereo spaces, the execution subject may perform ground estimation on the estimated ground point clouds in the second stereo spaces to obtain a plurality of ground sub-planes. Specifically, the executing subject may calculate a height average value of cloud points of each second stereo space, and then use the height average value as a ground sub-plane of the second stereo space.
In some optional implementations of this embodiment, the executive agent may determine the ground sub-plane by the following steps not shown in fig. 4: fitting estimated ground point cloud points in a plurality of second three-dimensional spaces to obtain a plurality of first planes; for each first plane, the following fitting steps are performed: selecting estimated ground point cloud points with the distance from the first plane being smaller than a first distance threshold value from a second three-dimensional space corresponding to the first plane as candidate point cloud points; fitting a second plane by using the candidate cloud points; determining whether the second plane is stable; and if the second plane is stable, taking the second plane as a ground sub-plane.
In this implementation, the execution main body may fit cloud points of each point in each second stereo space to obtain the first plane. Here, the cloud points of each point may be fitted by using an existing fitting method. Then for each first plane, the execution body may perform the following fitting steps.
Firstly, selecting estimated ground point cloud points with the distance from the first plane being less than a first distance threshold from a second three-dimensional space corresponding to the first plane, and taking the selected estimated ground point cloud points as candidate point cloud points.
The candidate cloud points are then used to fit a second plane.
It is to be understood that here, the fitting method employed for performing the main body may be the same as the fitting method when the first plane is obtained by fitting.
And finally, judging whether the second plane is stable. And if so, taking the second plane as a ground sub-plane of the second three-dimensional space.
And if the second plane is unstable, taking the second plane as a new first plane, and continuing to perform the fitting step.
Here, stable may mean that the angle between the second plane and the ground is smaller than a preset angle threshold. Or the number of the point cloud points falling on the second plane is larger than a preset number threshold.
In some optional implementations of this embodiment, the executive agent may determine whether the second plane is stable by the following steps not shown in fig. 4: determining whether the sum of the distances from the estimated ground point cloud points in the second stereo space to the second plane is less than a second distance threshold or not in response to the execution times of the fitting step being less than a preset time threshold; if the sum of the distances is smaller than a second distance threshold value, determining that the second plane is stable; if the sum of the distances is not less than the second distance threshold, the second plane is determined to be unstable.
In this implementation, the execution subject may record the number of times of execution of the fitting step. And under the condition of a preset number threshold of execution times, calculating the sum of the distances from the cloud points of each point in the second three-dimensional space to the second plane. And if the sum of the distances is less than a second distance threshold, the second plane is stable. If not, the second plane is not stable.
In some optional implementations of this embodiment, the execution body may derive the first plane by the following steps not shown in fig. 4: for each second three-dimensional space, sampling estimated ground point cloud points in the second three-dimensional space to obtain sampling point cloud points; and fitting the first plane by using sampling point cloud points.
In this implementation, the execution subject may sample cloud points of each point in the second three-dimensional space, and fit the sampled cloud points to obtain the first plane. In sampling, the execution subject may adopt various sampling modes, such as random sampling and the like. This can reduce the amount of calculation at the time of fitting.
In some optional implementations of this embodiment, the execution subject may implement the sampling of the cloud points of the points within the second stereo space by the following steps not shown in fig. 4: dividing the second three-dimensional space into a plurality of third three-dimensional spaces; and sampling the point cloud points in each third stereo space.
In this implementation, in order to ensure uniformity of sampling, the execution main body may first divide each second stereo space into a plurality of third stereo spaces when sampling. Then, the execution subject may take the same number of point cloud points in each third stereo space.
In some optional implementations of this embodiment, the method may further include the following steps not shown in fig. 4: and determining that the estimated ground point cloud points do not exist in the second stereo space in response to the execution times of the fitting step not being less than a preset time threshold.
In this implementation manner, if the execution times of the fitting step is not less than the preset time threshold, it is determined that the pre-estimated ground point cloud points do not exist in the second stereo space. The point cloud points in the second stereo space cannot be used when determining the predicted ground.
In some optional implementations of this embodiment, the method may further include the following steps not shown in fig. 4: and determining that the estimated ground point cloud points do not exist in the second three-dimensional space in response to that the execution times of the fitting step is not less than a preset time threshold and the angle between the second plane and the ground is greater than an angle threshold.
In this implementation manner, if the execution subject determines that the execution times of the fitting step is not less than the preset time threshold, and determines that the angle between the second plane obtained by executing the fitting step for the last time and the ground is greater than the angle threshold, the obtained second plane is considered to be unreasonable, and it can be determined that the estimated ground point cloud points do not exist in the second stereo space.
Atstep 404, a predicted ground is generated based on the plurality of ground sub-planes.
After obtaining the plurality of ground sub-planes, the executive agent may generate a predicted ground based on each ground sub-plane. Specifically, the execution main body can splice the sub-planes of each ground according to the positions of the sub-planes to obtain the predicted ground.
In some optional implementations of this embodiment, the execution subject may perform smoothing on the plurality of ground sub-planes to generate the predicted ground.
In some optional implementations of this embodiment, for each ground sub-plane, in the smoothing, the ground sub-plane around the ground sub-plane may be used to perform smoothing processing on the ground sub-plane.
In some optional implementation manners of this embodiment, for each ground sub-plane, during smoothing, an included angle between the ground sub-plane and the ground, an included angle between surrounding ground sub-planes and the ground, and a weight corresponding to each included angle may be calculated to calculate an included angle adjustment value between the ground sub-plane and the ground. And adjusting the included angle between the ground sub-plane and the ground according to the included angle adjusting value.
The method for outputting information provided by the embodiment of the application can obtain a more accurate prediction plane, so that the accuracy of the target ground threshold is improved.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for outputting information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 5, theapparatus 500 for outputting information of the present embodiment includes: a predictedground determination unit 501, a groundthreshold determination unit 502, an obstaclenumber determination unit 503, and a target groundthreshold determination unit 504.
A predictedground determining unit 501 configured to determine a predicted ground according to the point cloud data collected during the driving of the vehicle.
The groundthreshold determination unit 502 is configured to determine a plurality of ground thresholds according to a preset ground threshold value range.
The number-of-obstacles determining unit 503 is configured to determine, for each ground threshold, a ground point cloud from the predicted ground and the ground threshold, and perform obstacle identification on point clouds other than the ground point cloud in the point cloud data to determine the number of obstacles.
A target groundthreshold determination unit 504 configured to determine and output a target ground threshold according to the obtained plurality of numbers.
In some optional implementations of this embodiment, the groundthreshold determination unit 502 is further configured to: and selecting a plurality of points in the value range of the ground threshold value at preset distance intervals as a plurality of ground threshold values.
In some optional implementations of the present embodiment, the number ofobstacles determining unit 503 is further configured to: carrying out obstacle identification on point clouds except the ground point cloud in the point cloud data, and determining the size of an obstacle; and determining the number of obstacles with the height smaller than a preset height threshold value according to the size of the obstacles.
In some optional implementations of this embodiment, the target groundthreshold determination unit 504 is further configured to: determining a quantity-ground threshold curve according to the plurality of quantities and the ground threshold corresponding to each quantity; determining the slope of the curve at each ground threshold, and determining the target ground threshold according to each slope.
In some optional implementations of this embodiment, the target groundthreshold determination unit 504 is further configured to: determining the maximum value of the absolute values of the slopes; and taking the ground threshold corresponding to the maximum value as a target ground threshold.
In some optional implementations of the present embodiment, the predictionground determining unit 501 may further include a point cloud determining module, a space dividing module, a ground estimating module, and a ground generating module, which are not shown in fig. 5.
A point cloud determination module configured to determine an estimated ground point cloud from the point cloud data;
the space dividing module is configured to divide a first stereo space where the estimated ground point cloud is located into a plurality of second stereo spaces.
And the ground estimation module is configured to perform ground estimation on the estimated ground point clouds in the second stereo spaces to obtain a plurality of ground sub-planes.
A ground generation module configured to generate a predicted ground based on the plurality of ground sub-planes.
In some optional implementations of this embodiment, the point cloud determination module is further configured to: and taking point cloud points in the point cloud data within a preset height range of the estimated ground as the estimated ground point cloud.
In some optional implementations of this embodiment, the space division module is further configured to: dividing the estimated ground into a plurality of grids; and segmenting the first three-dimensional space based on the grids to obtain a plurality of second three-dimensional spaces.
In some optional implementations of this embodiment, the ground estimation module is further configured to: fitting estimated ground point cloud points in a plurality of second three-dimensional spaces to obtain a plurality of first planes; for each first plane, the following fitting steps are performed: selecting estimated ground point cloud points with the distance from the first plane being smaller than a first distance threshold value from a second three-dimensional space corresponding to the first plane as candidate point cloud points; fitting a second plane by using the candidate cloud points; determining whether the second plane is stable; and if the second plane is stable, taking the second plane as a ground sub-plane.
In some optional implementations of this embodiment, the ground estimation module is further configured to: in response to determining that the second plane is unstable, replacing the first plane with the second plane and continuing to perform the fitting step.
In some optional implementations of this embodiment, the ground estimation module is further configured to: for each second three-dimensional space, sampling estimated ground point cloud points in the second three-dimensional space to obtain sampling point cloud points; and fitting the first plane by using sampling point cloud points.
In some optional implementations of this embodiment, the ground estimation module is further configured to: dividing the second three-dimensional space into a plurality of third three-dimensional spaces; and sampling the estimated ground point cloud points in each third stereo space.
In some optional implementations of this embodiment, the ground estimation module is further configured to: determining whether the sum of the distances from the estimated ground point cloud points in the second stereo space to the second plane is less than a second distance threshold or not in response to the execution times of the fitting step being less than a preset time threshold; if the sum of the distances is smaller than a second distance threshold value, determining that the second plane is stable; if the sum of the distances is not less than the second distance threshold, the second plane is determined to be unstable.
In some optional implementations of the present embodiment, the predictionground determining unit 501 further includes: a first determining module configured to determine that there are no pre-estimated ground point cloud points in the second stereo space in response to the number of times the fitting step is performed being not less than a number of times threshold.
In some optional implementations of the present embodiment, the predictionground determining unit 501 further includes: and the second determining module is configured to determine that the estimated ground point cloud points do not exist in the second stereo space in response to the number of times of execution of the fitting step being not less than a preset number threshold and the angle between the second plane and the ground being greater than an angle threshold.
It should be understood that theunits 501 to 504, which are described in theapparatus 500 for outputting information, correspond to the respective steps in the method described with reference to fig. 2, respectively. Thus, the operations and features described above for the method for outputting information are equally applicable to theapparatus 500 and the units included therein and will not be described again here.
Referring now to FIG. 6, shown is a schematic diagram of anelectronic device 600 suitable for use in implementing embodiments of the present disclosure. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6,electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of theelectronic apparatus 600 are also stored. Theprocessing device 601, theROM 602, and the RAM603 are connected to each other via abus 604. An input/output (I/O)interface 605 is also connected tobus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.;output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like;storage 608 including, for example, tape, hard disk, etc.; and acommunication device 609. The communication means 609 may allow theelectronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates anelectronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from theROM 602. The computer program, when executed by theprocessing device 601, performs the above-described functions defined in the methods of embodiments of the present disclosure. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: determining a predicted ground according to point cloud data acquired by a vehicle in the driving process; determining a plurality of ground threshold values according to a preset ground threshold value range; for each ground threshold, determining ground point clouds according to the predicted ground and the ground threshold, and identifying obstacles in the point clouds except the ground point clouds in the point cloud data to determine the number of the obstacles; and determining and outputting the target ground threshold according to the obtained plurality of quantities.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a predicted ground determination unit, a ground threshold determination unit, a number of obstacles determination unit, and a target ground threshold determination unit. The names of the units do not form a limitation to the units themselves in some cases, and for example, the predicted ground determining unit may be described as a "unit for determining the predicted ground based on point cloud data collected during the driving of the vehicle".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (32)
1. A method for outputting information, comprising:
determining a predicted ground according to point cloud data acquired by a vehicle in the driving process;
determining a plurality of ground threshold values according to a preset ground threshold value range;
for each ground threshold, determining ground point clouds according to the predicted ground and the ground threshold, and identifying obstacles in the point clouds except the ground point clouds in the point cloud data to determine the number of the obstacles;
and determining and outputting the target ground threshold according to the obtained plurality of quantities.
2. The method of claim 1, wherein the determining a plurality of ground thresholds according to a preset ground threshold value range comprises:
and selecting a plurality of points in the value range of the ground threshold value at preset distance intervals as a plurality of ground threshold values.
3. The method of claim 1, wherein the identifying obstacles to the point clouds of the point cloud data other than the ground point cloud, determining the number of obstacles comprises:
performing obstacle identification on point clouds except the ground point cloud in the point cloud data, and determining the size of an obstacle;
and determining the number of obstacles with the height smaller than a preset height threshold value according to the size of the obstacles.
4. The method of claim 1, wherein said determining and outputting a target ground threshold from the derived plurality of quantities comprises:
determining a quantity-ground threshold curve according to the plurality of quantities and the ground threshold corresponding to each quantity;
determining slopes of the curve at each ground threshold, and determining a target ground threshold according to each slope.
5. The method of claim 4, wherein determining a target ground threshold from the slopes comprises:
determining the maximum value of the absolute values of the slopes;
and taking the ground threshold corresponding to the maximum value as a target ground threshold.
6. The method of any one of claims 1-5, wherein determining a predicted terrain from point cloud data collected during travel of the vehicle comprises:
determining estimated ground point cloud in the point cloud data;
dividing a first stereo space where the estimated ground point cloud is located into a plurality of second stereo spaces;
performing ground estimation on the estimated ground point clouds in the second three-dimensional spaces to obtain a plurality of ground sub-planes;
generating the predicted terrain based on the plurality of terrain sub-planes.
7. The method of claim 6, wherein said determining an estimated ground point cloud in said point cloud data comprises:
and taking the point cloud points in the point cloud data within a preset height range of the estimated ground as the estimated ground point cloud.
8. The method of claim 7, wherein the dividing the first stereo space in which the estimated ground point cloud is located into a plurality of second stereo spaces comprises:
dividing the estimated ground into a plurality of grids;
and segmenting the first three-dimensional space based on a plurality of grids to obtain a plurality of second three-dimensional spaces.
9. The method of claim 6, wherein said ground estimating the estimated ground point cloud within the second plurality of stereo spaces to obtain a plurality of ground sub-planes comprises:
fitting estimated ground point cloud points in a plurality of second three-dimensional spaces to obtain a plurality of first planes;
for each first plane, the following fitting steps are performed: selecting estimated ground point cloud points with the distance from the first plane being smaller than a first distance threshold value from a second three-dimensional space corresponding to the first plane as candidate point cloud points; fitting a second plane by using the candidate cloud points; determining whether the second plane is stable; and if the second plane is stable, taking the second plane as a ground sub-plane.
10. The method of claim 9, wherein said ground estimating estimated ground point cloud points in said second plurality of volumetric spaces resulting in a plurality of ground sub-planes, further comprises:
in response to determining that the second plane is unstable, replacing the first plane with the second plane and continuing to perform the fitting step.
11. The method of claim 9 wherein said fitting a plurality of first planes based on estimated ground point clouds in a plurality of second stereo spaces comprises:
for each second three-dimensional space, sampling estimated ground point cloud points in the second three-dimensional space to obtain sampling point cloud points;
and fitting the cloud points of the sampling points to a first plane.
12. The method of claim 11 wherein sampling the estimated ground point cloud points in the second stereo space comprises:
dividing the second three-dimensional space into a plurality of third three-dimensional spaces;
and sampling the estimated ground point cloud points in each third stereo space.
13. The method of claim 9, wherein said determining whether the second plane is stable comprises:
determining whether the sum of the distances from the cloud points of the estimated ground points in the second stereo space to the second plane is less than a second distance threshold or not in response to the execution times of the fitting step being less than a preset time threshold;
if the sum of the distances is smaller than the second distance threshold, determining that the second plane is stable;
and if the sum of the distances is not less than the second distance threshold, determining that the second plane is unstable.
14. The method of claim 13, wherein the method further comprises:
and determining that the estimated ground point cloud points do not exist in the second stereo space in response to the execution times of the fitting step not being less than the time threshold.
15. The method of claim 13, wherein the method further comprises:
and determining that the estimated ground point cloud points do not exist in the second three-dimensional space in response to that the execution times of the fitting step is not less than a preset time threshold and the angle between the second plane and the ground is greater than an angle threshold.
16. An apparatus for outputting information, comprising:
a predicted ground determination unit configured to determine a predicted ground from point cloud data collected during a driving of the vehicle;
the ground threshold value determining unit is configured to determine a plurality of ground threshold values according to a preset ground threshold value range;
the obstacle number determination unit is configured to determine a ground point cloud according to the predicted ground and the ground threshold for each ground threshold, and perform obstacle identification on point clouds except the ground point cloud in the point cloud data to determine the number of obstacles;
and the target ground threshold value determining unit is configured to determine and output a target ground threshold value according to the obtained plurality of quantities.
17. The apparatus of claim 16, wherein the ground threshold determination unit is further configured to:
and selecting a plurality of points in the value range of the ground threshold value at preset distance intervals as a plurality of ground threshold values.
18. The apparatus of claim 16, wherein the number of obstacles determination unit is further configured to:
performing obstacle identification on point clouds except the ground point cloud in the point cloud data, and determining the size of an obstacle;
and determining the number of obstacles with the height smaller than a preset height threshold value according to the size of the obstacles.
19. The apparatus of claim 16, wherein the target ground threshold determination unit is further configured to:
determining a quantity-ground threshold curve according to the plurality of quantities and the ground threshold corresponding to each quantity;
determining slopes of the curve at each ground threshold, and determining a target ground threshold according to each slope.
20. The apparatus of claim 19, wherein the target ground threshold determination unit is further configured to:
determining the maximum value of the absolute values of the slopes;
and taking the ground threshold corresponding to the maximum value as a target ground threshold.
21. The apparatus according to any one of claims 16-20, wherein the predictive terrain determination unit comprises:
a point cloud determination module configured to determine an estimated ground point cloud in the point cloud data;
a space dividing module configured to divide a first stereo space in which the estimated ground point cloud is located into a plurality of second stereo spaces;
a ground estimation module configured to perform ground estimation on the estimated ground point clouds in the second stereo spaces to obtain a plurality of ground sub-planes;
a ground generation module configured to generate the predicted ground based on the plurality of ground sub-planes.
22. The apparatus of claim 21, wherein the point cloud determination module is further configured to:
and taking the point cloud points in the point cloud data within a preset height range of the estimated ground as the estimated ground point cloud.
23. The apparatus of claim 21, wherein the spatial partitioning module is further configured to:
dividing the estimated ground into a plurality of grids;
and segmenting the first three-dimensional space based on a plurality of grids to obtain a plurality of second three-dimensional spaces.
24. The apparatus of claim 21, wherein the ground estimation module is further configured to:
fitting estimated ground point cloud points in a plurality of second three-dimensional spaces to obtain a plurality of first planes;
for each first plane, the following fitting steps are performed: selecting estimated ground point cloud points with the distance from the first plane being smaller than a first distance threshold value from a second three-dimensional space corresponding to the first plane as candidate point cloud points; fitting a second plane by using the candidate cloud points; determining whether the second plane is stable; and if the second plane is stable, taking the second plane as a ground sub-plane.
25. The apparatus of claim 24, wherein the ground estimation module is further configured to:
in response to determining that the second plane is unstable, replacing the first plane with the second plane and continuing to perform the fitting step.
26. The apparatus of claim 24, wherein the ground estimation module is further configured to:
for each second three-dimensional space, sampling estimated ground point cloud points in the second three-dimensional space to obtain sampling point cloud points;
and fitting the cloud points of the sampling points to a first plane.
27. The apparatus of claim 26, wherein the ground estimation module is further configured to:
dividing the second three-dimensional space into a plurality of third three-dimensional spaces;
and sampling the estimated ground point cloud points in each third stereo space.
28. The apparatus of claim 24, wherein the ground estimation module is further configured to:
determining whether the sum of the distances from the cloud points of the estimated ground points in the second stereo space to the second plane is less than a second distance threshold or not in response to the execution times of the fitting step being less than a preset time threshold;
if the sum of the distances is smaller than the second distance threshold, determining that the second plane is stable;
and if the sum of the distances is not less than the second distance threshold, determining that the second plane is unstable.
29. The apparatus of claim 28, wherein the predictive terrain determination unit further comprises:
a first determining module configured to determine that there are no estimated ground point cloud points in the second stereo space in response to the number of times the fitting step is performed being not less than the number threshold.
30. The apparatus of claim 28, wherein the predictive terrain determination unit further comprises:
and the second determining module is configured to determine that the estimated ground point cloud points do not exist in the second stereo space in response to the number of times of execution of the fitting step being not less than a preset number threshold and the angle between the second plane and the ground being greater than an angle threshold.
31. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-15.
32. A computer-readable medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method of any one of claims 1-15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910907185.7ACN112560548B (en) | 2019-09-24 | 2019-09-24 | Method and device for outputting information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910907185.7ACN112560548B (en) | 2019-09-24 | 2019-09-24 | Method and device for outputting information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112560548Atrue CN112560548A (en) | 2021-03-26 |
| CN112560548B CN112560548B (en) | 2024-04-02 |
Family
ID=75028981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910907185.7AActiveCN112560548B (en) | 2019-09-24 | 2019-09-24 | Method and device for outputting information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560548B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050015201A1 (en)* | 2003-07-16 | 2005-01-20 | Sarnoff Corporation | Method and apparatus for detecting obstacles |
| US20170357267A1 (en)* | 2016-06-10 | 2017-12-14 | Cnh Industrial America Llc | Autonomous work vehicle obstacle detection system |
| CN108501954A (en)* | 2018-04-03 | 2018-09-07 | 北京瑞特森传感科技有限公司 | A kind of gesture identification method, device, automobile and storage medium |
| CN109144097A (en)* | 2018-08-15 | 2019-01-04 | 广州极飞科技有限公司 | Barrier or ground identification and flight control method, device, equipment and medium |
| CN109766404A (en)* | 2019-02-12 | 2019-05-17 | 湖北亿咖通科技有限公司 | Points cloud processing method, apparatus and computer readable storage medium |
| CN109840448A (en)* | 2017-11-24 | 2019-06-04 | 百度在线网络技术（北京）有限公司 | Information output method and device for automatic driving vehicle |
| CN110121716A (en)* | 2017-04-28 | 2019-08-13 | 深圳市大疆创新科技有限公司 | Method and related system for network analysis |
- 2019
- 2019-09-24CNCN201910907185.7Apatent/CN112560548B/enactiveActive
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050015201A1 (en)* | 2003-07-16 | 2005-01-20 | Sarnoff Corporation | Method and apparatus for detecting obstacles |
| US20170357267A1 (en)* | 2016-06-10 | 2017-12-14 | Cnh Industrial America Llc | Autonomous work vehicle obstacle detection system |
| CN109154823A (en)* | 2016-06-10 | 2019-01-04 | 凯斯纽荷兰工业美国有限责任公司 | Utonomous working vehicle barrier detection system |
| CN110121716A (en)* | 2017-04-28 | 2019-08-13 | 深圳市大疆创新科技有限公司 | Method and related system for network analysis |
| CN109840448A (en)* | 2017-11-24 | 2019-06-04 | 百度在线网络技术（北京）有限公司 | Information output method and device for automatic driving vehicle |
| CN108501954A (en)* | 2018-04-03 | 2018-09-07 | 北京瑞特森传感科技有限公司 | A kind of gesture identification method, device, automobile and storage medium |
| CN109144097A (en)* | 2018-08-15 | 2019-01-04 | 广州极飞科技有限公司 | Barrier or ground identification and flight control method, device, equipment and medium |
| CN109766404A (en)* | 2019-02-12 | 2019-05-17 | 湖北亿咖通科技有限公司 | Points cloud processing method, apparatus and computer readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| LI P.等: "The Analysis of Stereo Vision 3D Point Cloud Data of Autonomous Vehicle Obstacle Recognition", 2015 7TH INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS, 23 November 2015 (2015-11-23)* |
| 张永博;李必军;陈诚;: "激光点云在无人驾驶路径检测中的应用", 测绘通报, no. 11, 25 November 2016 (2016-11-25)* |
| 陆峰;徐友春;李永乐;王德宇;谢德胜;: "基于信息融合的智能车障碍物检测方法", 计算机应用, no. 2, 20 December 2017 (2017-12-20)* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112560548B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110687549B (en) | Obstacle detection method and device | |
| CN112634181B (en) | Method and device for detecting ground point cloud points | |
| CN109521756B (en) | Obstacle motion information generation method and apparatus for unmanned vehicle | |
| CN112630799B (en) | Method and apparatus for outputting information | |
| CN109146976B (en) | Method and device for locating unmanned vehicles | |
| CN111602138B (en) | Object detection system and method based on artificial neural network | |
| JP6550403B2 (en) | Dynamic scene analysis method, associated analysis module and computer program | |
| CN113607185B (en) | Lane line information display method, device, electronic device and computer readable medium | |
| CN112622923B (en) | Method and apparatus for controlling a vehicle | |
| CN114022614B (en) | A method and system for estimating the confidence of three-dimensional reconstruction target position | |
| CN112558036B (en) | Method and device for outputting information | |
| CN110618413A (en) | Passable area detection method and device based on multi-line laser radar | |
| CN112630798B (en) | Method and apparatus for estimating ground | |
| CN112558035B (en) | Method and apparatus for estimating ground | |
| CN112560548A (en) | Method and apparatus for outputting information | |
| CN110363834B (en) | Point cloud data segmentation method and device | |
| CN113034562B (en) | Method and apparatus for optimizing depth information | |
| CN113987741A (en) | A multi-target data tracking method and system | |
| CN112634487B (en) | Method and apparatus for outputting information | |
| CN112668371A (en) | Method and apparatus for outputting information | |
| CN112630749A (en) | Method and device for outputting prompt information | |
| CN113650616B (en) | Vehicle behavior prediction method and system based on collected data | |
| CN119445137A (en) | Laser radar target frame detection method, device, electronic equipment and storage medium | |
| CN119942478A (en) | Vehicle target recognition method, system, vehicle and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |