Disclosure of Invention
The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a point cloud map updating method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a method for updating a point cloud map, where the method includes acquiring a real-time point cloud set corresponding to a target area during a process of moving from a first location to a second location in the target area, screening at least one real-time point cloud representing scene variation from the real-time point cloud set as a point cloud set to be processed, and updating a point cloud map associated with the target area according to the point cloud set to be processed.
Optionally, the screening at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed includes removing at least one of a first real-time point cloud subset and a second real-time point cloud subset from the real-time point cloud set to obtain a removed real-time point cloud set, and determining the removed real-time point cloud set as the point cloud set to be processed.
Optionally, the removing at least one of the first real-time point cloud subset and the second real-time point cloud subset from the real-time point cloud set to obtain a removed real-time point cloud set includes determining a point cloud set in which the real-time point cloud set is a static point cloud as the first real-time point cloud subset, determining a point cloud set in which the real-time point cloud set is a dynamic point cloud as the second real-time point cloud subset in response to detecting that the dynamic point cloud exists in the real-time point cloud set, and removing the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.
Optionally, the determining the point cloud set of the real-time point cloud set as the static point cloud as the first real-time point cloud subset includes determining at least one point cloud identical to the real-time point cloud set of the point cloud map as a target point cloud set in response to detecting that the point cloud identical to the point cloud set of the point cloud map exists, and determining the point cloud set associated with the target ground in the point cloud set of the point cloud map and the target point cloud set as the first real-time point cloud subset.
Optionally, the updating of the point cloud map associated with the target area according to the point cloud set to be processed includes obtaining a voxel grid information set corresponding to the target area and area information corresponding to each piece of voxel grid information in the voxel grid information set, determining voxel grid information corresponding to each piece of point cloud to be processed in the point cloud set to be processed according to the area information corresponding to each piece of voxel grid information in the voxel grid information set to obtain a voxel grid information subset, determining point cloud change area information in the target area according to the voxel grid information subset, and updating the point cloud map according to the point cloud change area information.
The method comprises the steps of determining a point cloud change area in a target area according to a voxel grid information subset, obtaining index information corresponding to each piece of voxel grid information in the voxel grid information set, determining index information corresponding to each piece of voxel grid information in the voxel grid information subset according to the index information corresponding to each piece of voxel grid information in the voxel grid information set to obtain an index information set, determining the point cloud association times corresponding to each piece of index information in the index information set, determining index information, which is used for determining that the point cloud association times corresponding to at least one piece of index information in the index information set are larger than a first target numerical value, of meeting preset conditions, as target index information, and determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.
Optionally, the method further comprises determining, for each index information in the index information set, an addition result of the point cloud association number corresponding to the index information and the second target value as the point cloud association number corresponding to the index information.
Optionally, the determining the point cloud variation area in the target area according to the voxel grid information subset includes determining a point cloud association number corresponding to each piece of voxel grid information in the voxel grid information subset, and determining, as first target voxel grid information, voxel grid information with the point cloud association number satisfying a predetermined condition in the at least one piece of voxel grid information in response to the fact that the point cloud association number corresponding to the at least one piece of voxel grid information in the voxel grid information subset is greater than a first target value, to obtain a first target voxel grid information set.
Optionally, the method further comprises determining, for each voxel grid information in the voxel grid information subset, the addition result of the point cloud association times corresponding to the voxel grid information and the second target value as the point cloud association times corresponding to the voxel grid information.
Optionally, the method further comprises storing the first target voxel grid information set, and determining a region corresponding to the first target voxel grid information set as a point cloud change region in the target region.
Optionally, determining the voxel grid information corresponding to each of the point clouds to be processed in the point cloud set to be processed according to the region information corresponding to each of the voxel grid information in the point cloud set to be processed to obtain a voxel grid information subset, wherein the method comprises the steps of carrying out coordinate transformation on each of the point clouds to be processed in the point cloud set to be processed to generate corresponding map coordinates to obtain a map coordinate set, and determining the voxel grid information corresponding to each of the point clouds to be processed in the point cloud set to be processed according to the map coordinate set and the region information corresponding to each of the voxel grid information in the voxel grid information set to obtain the voxel grid information subset.
In a second aspect, some embodiments of the present disclosure provide a point cloud map updating apparatus, including an acquisition unit configured to acquire a real-time point cloud set corresponding to a target area in a process of moving from a first location to a second location within the target area, a screening unit configured to screen at least one real-time point cloud representing scene changes from the real-time point cloud set as a point cloud set to be processed, and an updating unit configured to update a point cloud map associated with the target area according to the point cloud set to be processed.
Optionally, the screening unit is further configured to remove at least one of the first real-time point cloud subset and the second real-time point cloud subset from the real-time point cloud set to obtain a removed real-time point cloud set, and determine the removed real-time point cloud set as the point cloud set to be processed.
Optionally, the screening unit is further configured to determine a point cloud set of the real-time point cloud set as a static point cloud as the first real-time point cloud subset, determine a point cloud set of the real-time point cloud set as a dynamic point cloud as the second real-time point cloud subset in response to detecting that the dynamic point cloud exists in the real-time point cloud set, and remove the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.
Optionally, the screening unit is further configured to determine, as the target point cloud, at least one point cloud identical between the point cloud corresponding to the point cloud map and the real-time point cloud, and to determine, as the first real-time point cloud subset, a point cloud associated with a target ground in the point cloud set corresponding to the point cloud map and the target point cloud, in response to detecting that the same point cloud exists between the point cloud corresponding to the point cloud map and the real-time point cloud.
Optionally, the updating unit is further configured to acquire a voxel grid information set corresponding to the target area and area information corresponding to each piece of voxel grid information in the voxel grid information set, determine voxel grid information corresponding to each piece of point cloud to be processed in the point cloud set to be processed according to the area information corresponding to each piece of voxel grid information in the voxel grid information set to obtain a voxel grid information subset, determine point cloud change area information in the target area according to the voxel grid information subset, and update the point cloud map according to the point cloud change area information.
Optionally, the updating unit is further configured to obtain index information corresponding to each piece of voxel grid information in the voxel grid information set, determine index information corresponding to each piece of voxel grid information in the voxel grid information subset according to the index information corresponding to each piece of voxel grid information in the voxel grid information set to obtain an index information set, determine a point cloud association number corresponding to each piece of index information in the index information set, determine, as target index information, index information with the point cloud association number satisfying a predetermined condition in the at least one piece of index information set in response to determining that the point cloud association number corresponding to at least one piece of index information in the index information set is greater than a first target value, and determine the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.
Optionally, the updating unit is further configured to determine, for each index information in the set of index information, an addition result of the point cloud association number corresponding to the index information and the second target value as the point cloud association number corresponding to the index information.
Optionally, the updating unit is further configured to determine a point cloud association number corresponding to each piece of voxel grid information in the voxel grid information subset, and determine, as the first target voxel grid information, voxel grid information with the point cloud association number satisfying a predetermined condition in the at least one piece of voxel grid information in response to the fact that the point cloud association number corresponding to the at least one piece of voxel grid information in the voxel grid information subset is greater than a target value, to obtain a first target voxel grid information set.
Optionally, the updating unit is further configured to determine, for each voxel grid information in the voxel grid information subset, an addition result of the point cloud association number corresponding to the voxel grid information and the target value as the point cloud association number corresponding to the voxel grid information.
Optionally, the updating unit is further configured to store the first target voxel grid information set and to determine a region corresponding to the first target voxel grid information set as a point cloud variation region in the target region.
Optionally, the updating unit is further configured to perform coordinate transformation on each point cloud to be processed in the point cloud set to be processed to generate corresponding map coordinates to obtain a map coordinate set, and determine voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and region information corresponding to each piece of voxel grid information in the voxel grid information set to obtain a voxel grid information subset.
In a third aspect, some embodiments of the present disclosure provide an electronic device comprising one or more processors, a storage device having one or more programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement a method as described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program when executed by a processor implements a method as described in any of the implementations of the first aspect.
The method for updating the point cloud map has the advantages that the point cloud map to be processed can be determined quickly and efficiently. Furthermore, the point cloud map can be updated, so that the point cloud map is more accurate. Specifically, the accuracy of determining the transformation area by manual monitoring is low, which may cause problems such as missing report and hysteresis. Therefore, the accuracy of the subsequent point cloud map is low. In addition, the manner of manual monitoring is time-consuming and labor-consuming. Based on this, the point cloud map updating method according to some embodiments of the present disclosure may acquire a real-time point cloud set corresponding to a target area in a process of moving from a first location to a second location within the target area. Here, a real-time point cloud set corresponding to the target area is acquired as data support for determining an area where scene change occurs in the point cloud map. And then, screening at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed. By determining the point cloud set to be processed, the scene change area in the point cloud map can be accurately determined later. And the updating of the subsequent point cloud map is more targeted. The side surface also improves the updating efficiency of the point cloud map. And finally, updating the point cloud map associated with the target area according to the point cloud set to be processed so as to enable the point cloud map to be more accurate.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1-2 are schematic diagrams of one application scenario of a point cloud map updating method according to some embodiments of the present disclosure.
In the application scenario of fig. 1-2, the electronic device 101 may first obtain the real-time point cloud 105 corresponding to the target area 102 during the moving from the first location 103 to the second location 104 in the target area 102. In this application scenario, the real-time point cloud 105 may include a real-time point cloud 1051, a real-time point cloud 1052, a real-time point cloud 1053, a real-time point cloud 1054, and a real-time point cloud 1055. The real-time point clouds in the real-time point cloud set 105 may be point clouds corresponding to objects in the scene corresponding to the target area 102. Then, at least one real-time point cloud 106 characterizing scene changes is screened from the above-mentioned real-time point cloud 105 as a point cloud 107 to be processed. In the present application scenario, real-time point clouds 1052, 1053, and 1054 are screened from real-time point clouds 105. The real-time point cloud 1052, the real-time point cloud 1053, and the real-time point cloud 1054 in the at least one real-time point cloud 106 may be point clouds corresponding to at least one object in the scene that changes in the target area 102. The real-time point cloud 1052 is determined to be the point cloud 1071 to be processed. The real time point cloud 1053 is determined as the point cloud 1072 to be processed. The real time point cloud 1054 is determined to be the point cloud 1073 to be processed. Finally, according to the point cloud set 107 to be processed, the point cloud map 108 associated with the target area 102 is updated, so that an updated point cloud map 109 can be obtained.
Note that, the electronic device 101 may be hardware, or may be software. When the electronic device is hardware, the electronic device may be implemented as a distributed cluster formed by a plurality of servers or terminal devices, or may be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it may be installed in the above-listed hardware device. It may be implemented as a plurality of software or software modules, for example, for providing distributed services, or as a single software or software module. The present invention is not particularly limited herein.
It should be understood that the number of electronic devices in fig. 1-2 is merely illustrative. There may be any number of electronic devices as desired for an implementation.
With continued reference to fig. 3, a flow 300 of some embodiments of a point cloud map updating method according to the present disclosure is shown. The point cloud map updating method comprises the following steps:
Step 301, acquiring a real-time point cloud set corresponding to a target area in the process of moving from a first place to a second place in the target area.
In some embodiments, the execution body of the point cloud map updating method (for example, the electronic device shown in fig. 1 or fig. 2) may acquire the real-time point cloud set corresponding to the target area during the process of moving from the first location to the second location in the target area. The target area may be a predetermined area where whether the scene to be checked is transformed or not. The first location may be a start location of a route within the target area. The second location may be a termination location of a route within the target area. In the process of moving from the first location to the second location in the target area, it is necessary to acquire a real-time point cloud set corresponding to each of a plurality of moments to determine an area in the target area where scene change occurs. The real-time point cloud set corresponding to a certain moment can embody scene layout information of the current scene.
As an example, the executing body may receive a real-time point cloud set transmitted from the point cloud collecting terminal in a process of moving from a first location to a second location within the target area. The point cloud collecting terminal may be a graph collecting device equipped with sensors such as a high-precision laser radar and an inertial navigation sensor, for example, an unmanned delivery vehicle, an unmanned vehicle, etc.
Step 302, screening at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed.
In some embodiments, the executing entity may screen at least one real-time point cloud characterizing scene changes from the real-time point cloud set as a point cloud set to be processed. Each of the at least one real-time point cloud may be a point cloud for which a scene in the target area may change with respect to the point cloud map.
As an example, the executing entity may screen at least one real-time point cloud characterizing scene changes from the set of real-time point clouds in various ways as a point cloud set to be processed.
And step 303, updating the point cloud map associated with the target area according to the point cloud set to be processed.
In some embodiments, the executing body may update the point cloud map associated with the target area according to the point cloud set to be processed.
As an example, the updating, by the execution subject, the point cloud map associated with the target area according to the point cloud set to be processed may include the following steps:
and a first step of determining a region set to be processed according to the point cloud set to be processed. The area to be processed may be an area formed by taking the point cloud to be processed as a center and taking the target value as a radius.
And secondly, performing real-time point cloud rescanning on each to-be-processed area in the to-be-processed area set in the point cloud map so as to update the point cloud map.
The point cloud map updating method of some embodiments of the present disclosure can quickly and efficiently determine the point cloud set to be processed. Furthermore, the point cloud map can be updated, so that the point cloud map is more accurate. Specifically, the accuracy of determining the transformation area by manual monitoring is low, which may cause problems such as missing report and hysteresis. Therefore, the accuracy of the subsequent point cloud map is low. In addition, the manner of manual monitoring is time-consuming and labor-consuming. Based on this, the point cloud map updating method according to some embodiments of the present disclosure may acquire a real-time point cloud set corresponding to a target area in a process of moving from a first location to a second location within the target area. Here, a real-time point cloud set corresponding to the target area is acquired as data support for determining an area where scene change occurs in the point cloud map. And then, screening at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed. By determining the point cloud set to be processed, the scene change area in the point cloud map can be accurately determined later. And the updating of the subsequent point cloud map is more targeted. The side surface also improves the updating efficiency of the point cloud map. And finally, updating the point cloud map associated with the target area according to the point cloud set to be processed so as to enable the point cloud map to be more accurate.
With further reference to fig. 4, a flow 400 of further embodiments of a point cloud map updating method according to the present disclosure is shown. The point cloud map updating method comprises the following steps:
Step 401, acquiring a real-time point cloud set corresponding to a target area in the process of moving from a first place to a second place in the target area.
In some embodiments, the specific implementation of step 401 and the technical effects thereof may refer to step 301 in the embodiment corresponding to fig. 3, which is not described herein again.
Step 402, removing at least one of the first real-time point cloud subset, the second real-time point cloud subset and the third real-time point cloud subset from the real-time point cloud set, and obtaining a removed real-time point cloud set.
In some embodiments, an executing body (e.g., the electronic device shown in fig. 1) may remove at least one of the first real-time point cloud subset and the second real-time point cloud subset from the real-time point cloud set, resulting in a removed real-time point cloud set.
As an example, the executing body may remove the first real-time point cloud subset from the real-time point cloud set, to obtain a removed real-time point cloud set.
In some optional implementations of some embodiments, the removing at least one of the first real-time point cloud subset and the second real-time point cloud subset from the real-time point cloud set to obtain a removed real-time point cloud set may include the following steps:
In the first step, the executing body may determine a point cloud set of the real-time point clouds as a static point cloud set as the first real-time point cloud subset. The point cloud set in the point cloud map, which is a static point cloud, may be a point cloud set corresponding to at least one object in a scene that does not change in the target area.
In response to detecting that the real-time point cloud set has a dynamic point cloud, the executing body may determine a point cloud set in which the real-time point cloud set is the dynamic point cloud as the second real-time point cloud subset. The point cloud set in the point cloud map, which is a dynamic point cloud, may be a point cloud set corresponding to at least one object in a scene that changes in a target area in a short time. The executing body can detect whether dynamic point clouds exist in the real-time point cloud set through the sensing module. For example, the at least one object in the scene that changes in a short time may include pedestrians and vehicles.
And thirdly, the execution body may remove the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.
Optionally, the determining the point cloud set of the real-time point clouds as the static point cloud set as the first real-time point cloud subset may include the following steps:
In response to detecting that the same point cloud exists between the point cloud corresponding to the point cloud map and the real-time point cloud, the execution subject may determine at least one point cloud that is the same between the point cloud corresponding to the point cloud map and the real-time point cloud as the target point cloud.
In the second step, the execution body may determine a point cloud set associated with a target ground among the point cloud sets corresponding to the point cloud map and the target point cloud set as the first real-time point cloud subset. Wherein the target ground-associated point cloud may be a point cloud characterizing target ground information.
And step 403, determining the removed real-time point cloud set as the point cloud set to be processed.
In some embodiments, the executing entity may determine the removed real-time point cloud set as the point cloud set to be processed.
Step 404, acquiring a voxel grid information set corresponding to the target region and region information corresponding to each voxel grid information in the voxel grid information set.
In some embodiments, the executing body may acquire a voxel grid information set corresponding to the target region and region information corresponding to each voxel grid information in the voxel grid information set. Wherein the target region may be divided into a plurality of voxel grids. Each voxel grid corresponds to voxel grid information. The voxel grid information may be location information where the voxel grid is located. For example, the position information may be coordinates corresponding to the voxel grid. Each of the plurality of voxel grids may be a three-dimensional volumetric region. For example, the voxel grid may be a cube of a fixed size. Thus, each voxel grid corresponds to a cube region. The region information of the voxel grid may be information of a region surrounded by respective coordinates corresponding to the voxel grid. By way of example, the coordinate set corresponding to the voxel grid may include (1, 1), (1, 3), (4, 1), (4, 3). The region information corresponding to the voxel grid may be such that the value of the abscissa is between 1 and 4 and the value of the ordinate is between 1 and 3.
It should be noted that the above target region may be divided into each voxel grid by:
First, determining a map coordinate system corresponding to a point cloud map.
And secondly, determining the target point from the map coordinate system as a reference center divided into each voxel grid. For example, the target point may be a center point in the target area moving from the first location to the second location.
Third, the size of the edges in the voxel grid is determined.
As an example, the size of the edges in the voxel grid may be set in accordance with the resolution of the reference point cloud map and the real-time point cloud. As an example, the size of the edge of the voxel grid may be 0.15-0.3 meters.
And fourthly, dividing the target area into various voxel grids according to the sizes of edges in the voxel grids and the reference center.
Step 405, determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the region information corresponding to each piece of voxel grid information in the voxel grid information set, and obtaining a voxel grid information subset.
In some embodiments, the executing body may determine voxel grid information corresponding to each of the point clouds to be processed in the point cloud set to be processed according to the region information corresponding to each of the voxel grid information in the voxel grid information set, so as to obtain a voxel grid information subset.
As an example, the executing body may compare the coordinates of each point cloud to be processed in the point cloud set to the area information of each voxel grid in the voxel grid set, so as to obtain a voxel grid information subset.
In some optional implementations of some embodiments, determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the region information corresponding to each piece of voxel grid information in the voxel grid information set to obtain a voxel grid information subset includes:
And performing coordinate conversion on each point cloud to be processed in the point cloud set to be processed to generate corresponding map coordinates, thereby obtaining a map coordinate set. The coordinates of each real-time point cloud in the acquired real-time point cloud set are coordinates in a real-time point cloud coordinate system. The point cloud to be processed is also the coordinates in the real-time point cloud coordinate system. Thus, the point cloud to be processed needs to be subjected to coordinate conversion into coordinates in a map coordinate system for determining the subsequent voxel grid information.
And a second step of determining voxel grid information corresponding to each point cloud to be processed in the point cloud set to be processed according to the map coordinate set and the region information corresponding to each piece of voxel grid information in the voxel grid information set, and obtaining a voxel grid information subset.
As an example, the executing entity may compare each map coordinate in the map coordinate set with the region information of each voxel grid in the voxel grid set, and may obtain a voxel grid information subset.
And step 406, determining the point cloud change area information in the target area according to the voxel grid information subset.
In some embodiments, the executing entity may determine the point cloud variation area information in the target area according to the voxel grid information subset.
As an example, the executing body may first fuse the region information corresponding to each voxel grid in the voxel grid subset to obtain fused region information. Then, the fused area information is determined as the point cloud fluctuation area information in the target area.
In some optional implementations of some embodiments, the determining the point cloud variation area in the target area according to the voxel grid information subset may include the steps of:
First, obtaining index information corresponding to each piece of voxel grid information in the voxel grid information set. The index information corresponding to the voxel grid information may be determined according to each coordinate corresponding to the voxel grid. The index information may be an index value.
As an example, the respective coordinates corresponding to the voxel grid information are (1, 1), (1, 3), (4, 1), (4, 3). Thus, the index value corresponding to the voxel grid information may be 2.25.
And a second step of determining index information corresponding to each piece of voxel grid information in the voxel grid information subset according to the index information corresponding to each piece of voxel grid information in the voxel grid information set to obtain an index information set.
And thirdly, determining the point cloud association times corresponding to each index information in the index information set. The number of times of point cloud association is the number of times associated with each real-time point cloud in the real-time point cloud set corresponding to at least one time point before the current time point.
As an example, the executing entity may determine the point cloud association times corresponding to the respective index information in the index information set by querying a table representing the association relationship between the index information and the point cloud association times.
It should be noted that, in order to improve the efficiency of searching and searching, voxel grid information may be stored by using a hash table. The keys in the hash table may be index information of the voxel grid. The key value in the hash table may be the number of point cloud associations.
And fourthly, in response to determining that the point cloud association times corresponding to at least one piece of index information in the index information set are larger than a first target value, determining the index information, of which the point cloud association times meet a preset condition, in the at least one piece of index information as target index information, and obtaining a target index information set. For example, the first target value may be "0".
As an example, in response to determining that there is at least one index information in the index information set that the number of point cloud associations corresponding to the at least one index information is greater than the first target value, the executing body may determine index information in the at least one index information that the number of point cloud associations is greater than a predetermined threshold as target index information, and obtain a target index information set.
And fifthly, determining the voxel grid information set corresponding to the target index information set as the first target voxel grid information set.
Optionally, the step further includes, for each index information in the index information set, the execution body determining, as the point cloud association number corresponding to the index information, an addition result of the point cloud association number corresponding to the index information and the second target value. As an example, the second target value may be 1.
In some optional implementations of some embodiments, the determining the point cloud variation area in the target area according to the voxel grid information subset may include the steps of:
And a first step of determining the point cloud association times corresponding to each piece of voxel grid information in the voxel grid information subset.
As an example, the executing entity may determine the number of point cloud associations corresponding to each voxel grid information in the subset of voxel grid information by querying a pre-constructed table characterizing the association relationship between voxel grid information and the number of point cloud associations.
And a second step of determining, as first target voxel grid information, voxel grid information with point cloud association times satisfying a predetermined condition in the at least one piece of voxel grid information in response to the fact that the point cloud association times corresponding to the at least one piece of voxel grid information in the voxel grid information subset are larger than a first target value, and obtaining a first target voxel grid information set.
As an example, in response to the at least one voxel grid information in the subset of voxel grid information having a point cloud association number greater than a first target value, the executing entity may determine voxel grid information having a point cloud association number greater than a predetermined threshold as first target voxel grid information, to obtain a first target set of voxel grid information.
Optionally, the step further includes, for each piece of voxel grid information in the voxel grid information subset, the execution body may determine an addition result of the point cloud association number corresponding to the piece of voxel grid information and the second target value as the point cloud association number corresponding to the piece of voxel grid information. As an example, the second target value may be "1".
Optionally, the executing body may store the first target voxel grid information set, and determine a region corresponding to the first target voxel grid information set as a point cloud variation region in the target region.
As an example, the execution body may store the first target voxel grid information set in a buffer.
Step 407, updating the point cloud map according to the point cloud change area information.
In some embodiments, the executing entity may update the point cloud map according to the point cloud change area information.
As an example, the execution subject may perform point cloud update on the point cloud change area corresponding to the point cloud change area information in the point cloud map.
As can be seen in fig. 4, the specific steps of determining the point cloud to be processed and determining the point cloud change area information are highlighted by the flow 400 of the point cloud map updating method in some embodiments corresponding to fig. 4, compared to the description of some embodiments corresponding to fig. 3. Therefore, the schemes described in these embodiments can more accurately and efficiently determine the point cloud to be processed, and according to the point cloud to be processed, the point cloud change area information in the target area can be more accurately determined. Therefore, the point cloud map is updated according to the point cloud change area information, so that the point cloud map is more accurate.
With further reference to fig. 5, as an implementation of the method shown in the foregoing figures, the present disclosure provides some embodiments of a point cloud map updating apparatus, which correspond to those method embodiments shown in fig. 3, and the apparatus is particularly applicable to various electronic devices.
As shown in fig. 5, a point cloud map updating apparatus 500 includes an acquisition unit 501, a screening unit 502, and an updating unit 503. Wherein the acquiring unit 501 is configured to acquire a real-time point cloud set corresponding to a target area in a process of moving from a first place to a second place in the target area, the screening unit 502 is configured to screen at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed, and the updating unit 503 is configured to update a point cloud map associated with the target area according to the point cloud set to be processed.
In some optional implementations of some embodiments, the filtering unit 502 in the point cloud map updating apparatus 500 is further configured to remove at least one of the first real-time point cloud subset and the second real-time point cloud subset from the real-time point cloud set, resulting in a removed real-time point cloud set, and determine the removed real-time point cloud set as the point cloud set to be processed.
In some optional implementations of some embodiments, the filtering unit 502 in the point cloud map updating apparatus 500 is further configured to determine a point cloud set of the real-time point cloud set as a static point cloud as the first real-time point cloud subset, determine a point cloud set of the real-time point cloud set as a dynamic point cloud as the second real-time point cloud subset in response to detecting that the dynamic point cloud exists in the real-time point cloud set, and remove the first real-time point cloud subset and the second real-time point cloud subset in the real-time point cloud set to obtain the removed real-time point cloud set.
In some optional implementations of some embodiments, the filtering unit 502 in the point cloud map updating apparatus 500 is further configured to determine, as the target point cloud, at least one point cloud identical between the point cloud corresponding to the point cloud map and the real-time point cloud in response to detecting that the same point cloud exists between the point cloud corresponding to the point cloud map and the real-time point cloud, and determine, as the first real-time point cloud subset, a point cloud associated with a target ground in the point cloud set corresponding to the point cloud map and the target point cloud.
In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to obtain a set of voxel grid information corresponding to the target area and area information corresponding to each piece of voxel grid information in the set of voxel grid information, determine voxel grid information corresponding to each piece of point cloud to be processed in the set of point clouds to be processed according to the area information corresponding to each piece of voxel grid information in the set of voxel grid information, obtain a subset of voxel grid information, determine point cloud change area information in the target area according to the subset of voxel grid information, and update the point cloud map according to the point cloud change area information.
In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to obtain index information corresponding to each piece of voxel grid information in the set of voxel grid information, determine index information corresponding to each piece of voxel grid information in the subset of voxel grid information according to the index information corresponding to each piece of voxel grid information in the set of voxel grid information to obtain an index information set, determine a number of point cloud associations corresponding to each piece of index information in the set of index information, determine, as target index information, index information that the number of point cloud associations in the set of at least one piece of index information satisfies a predetermined condition in response to determining that the number of point cloud associations in the set of index information is greater than a first target value, and determine the set of voxel grid information corresponding to the target index information set as the first target set of voxel grid information.
In some optional implementations of some embodiments, the point cloud map updating apparatus 500 further includes a first determining unit (not shown in the figure). The first determining unit may be configured to determine, for each index information in the index information set, an addition result of the point cloud association number corresponding to the index information and the second target value as the point cloud association number corresponding to the index information.
In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to determine a number of point cloud associations corresponding to each voxel grid information in the subset of voxel grid information, and determine, as the first target voxel grid information, voxel grid information in which the number of point cloud associations satisfies a predetermined condition in the at least one voxel grid information in response to the number of point cloud associations corresponding to the at least one voxel grid information being greater than the first target value, to obtain the first target set of voxel grid information.
In some optional implementations of some embodiments, the point cloud map updating apparatus 500 further includes a second determining unit (not shown in the figure). Wherein the second determining unit may be configured to determine, for each voxel grid information in the voxel grid information subset, an addition result of the point cloud association number corresponding to the voxel grid information and the second target value as the point cloud association number corresponding to the voxel grid information.
In some optional implementations of some embodiments, the point cloud map updating apparatus 500 further includes a storage determining unit (not shown in the figure). The storage determination unit may be configured to store the first target voxel grid information set, and determine a region corresponding to the first target voxel grid information set as a point cloud fluctuation region in the target region.
In some optional implementations of some embodiments, the updating unit 503 in the point cloud map updating apparatus 500 is further configured to perform coordinate transformation on each of the point clouds to be processed to generate corresponding map coordinates to obtain a map coordinate set, and determine voxel grid information corresponding to each of the point clouds to be processed according to the map coordinate set and region information corresponding to each of the voxel grid information in the voxel grid information set to obtain a voxel grid information subset.
It will be appreciated that the elements described in the apparatus 500 correspond to the various steps in the method described with reference to fig. 3. Thus, the operations, features and resulting benefits described above with respect to the method are equally applicable to the apparatus 500 and the units contained therein, and are not described in detail herein.
Referring now to fig. 6, a schematic diagram of an electronic device 600 (e.g., the electronic device of fig. 1) suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.
As shown in fig. 6, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to 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 required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
In general, devices may be connected to I/O interface 605 including input devices 606, including for example, touch screens, touch pads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc., output devices 607, including for example, liquid Crystal Displays (LCDs), speakers, vibrators, etc., storage devices 608, including for example, magnetic tape, hard disk, etc., and communication devices 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 6 may represent one device or a plurality of devices as needed.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some 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 shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 609, or from storage device 608, or from ROM 602. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing device 601.
It should be noted that, in some embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of a 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 some embodiments of the present 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 some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. 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 wiring, fiber optic cable, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be included in the electronic device or may exist alone without being incorporated 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 acquire a real-time point cloud set corresponding to a target area during a process of moving from a first place to a second place in the target area, screen at least one real-time point cloud representing scene change from the real-time point cloud set as a point cloud set to be processed, and update a point cloud map associated with the target area according to the point cloud set to be processed.
Computer program code for carrying out operations for some embodiments of the present disclosure may be written in 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 kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts 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 some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example as a processor comprising an acquisition unit, a screening unit and an updating unit. The names of these units do not limit the unit itself in some cases, and for example, the acquisition unit may also be described as "a unit that acquires a real-time point cloud set corresponding to a target area in the process of moving from a first location to a second location within the target area".
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic that may be used include Field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems-on-a-chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being 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 technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.