Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The driving behavior early warning method provided by the embodiment of the application can be applied to the road side equipment shown in the figure 1. The road side equipment can be an intelligent base station (which refers to an important infrastructure of intelligent traffic road cooperation, is a service station integrating sensing, calculating and communication capabilities, and is also called a road side fusion sensing system or a road side base station). The roadside devices may include a device 102 for acquiring image information and a device 104 for acquiring point cloud information and a computer device 106 connected to both the device 102 for acquiring image information and the device 104 for acquiring point cloud information. The device 102 for acquiring image information may be a camera, and the device 104 for acquiring point cloud information may be a laser radar or a millimeter wave radar. In the present embodiment, a camera and a laser radar are described as examples.
Specifically, the laser radar can collect target data in the laser radar visual field range at each moment, and transmit the obtained laser point cloud data to the computer equipment for processing; meanwhile, the camera can acquire target data in the visual field range of the camera at all times and transmit the acquired image data to the computer equipment for processing. The number of the laser radars and the number of the cameras can be one or more, and the laser radars can be set according to actual road conditions. The computer device may be a stand-alone terminal or server, or may be an integrated device integrated into the lidar or the camera, and is not particularly limited herein.
In one embodiment, as shown in fig. 2, a driving behavior early warning method is provided, and this embodiment relates to a specific process of how to predict dangerous behaviors of a current driving behavior of a target vehicle. Taking the method applied to the road side equipment in fig. 1 as an example for illustration, the method may include the following steps:
S202, acquiring a current first tracking result and a current second tracking result of the target vehicle, which are obtained after the target vehicle is tracked by the image data and the point cloud data respectively.
Currently, road side equipment is arranged on a road section corresponding to each road, and a visual field range corresponding to a camera in the road side equipment is recorded as a camera visual field range. The image data collected at each moment can be obtained by collecting the images of each vehicle at each moment on the road section through a camera, and the image data are generally continuous multi-frame image data, namely one moment can correspond to one frame of image data, and a plurality of moments correspond to the multi-frame image data.
After the camera acquires the image data of each vehicle at each moment, the image data at each moment can be transmitted to the computer equipment in the road side equipment, then the computer equipment can detect the image data at each moment of each vehicle to obtain a first detection result of the target vehicle at each moment, and further track the plurality of first detection results to obtain a first tracking result of the target vehicle corresponding to the detection result. Specifically, based on the above principle, at the current time, the computer device performs detection processing on the acquired image data, and tracks the first detection result after the detection processing to obtain a current first tracking result at the current time.
The current first tracking result may include vehicle information (e.g., license plate number, etc.) of the target vehicle, category information, bounding box information, first tracking trajectory, etc. For example, the bounding box may include a length, a width, etc. of the bounding box, and may also include position information of the target vehicle, a color of the target vehicle, a model of the target vehicle, etc.
Of course, before the computer device performs the detection processing on the image data of each time of each vehicle, the normalization processing may be performed on the image data, and the image data may be adjusted to a fixed size so as to perform the processing in a unified manner. The detection process may then continue for this fixed size image data.
Further, the field of view corresponding to the laser radar in the roadside device is denoted as the laser radar field of view. The point cloud data acquired at each moment can be obtained by acquiring the point cloud data of the vehicles at each moment on the road section through the laser radar. And then, the laser radar can send the acquired point cloud data at all times to computer equipment in the road side equipment. The computer equipment can carry out voxelization processing on the point cloud data corresponding to each moment, then carry out detection processing on the point cloud data of each moment by adopting a three-dimensional target detection algorithm to obtain second detection results of the target vehicle at each moment, and further carry out tracking processing on a plurality of second detection results to obtain second tracking results of the target vehicle corresponding to the detection results. Specifically, based on the above principle, at the current moment, the computer device performs detection processing on the obtained point cloud data, and after tracking the second detection result after the detection processing, obtains the current second tracking result at the current moment. The current second tracking result may include position information, speed information, heading angle information, a second tracking trajectory, etc. of the target vehicle at the current time.
The target vehicle obtained by the detection processing of the image data and the point cloud data may be one or more, and typically a plurality of target vehicles.
S204, determining a current target tracking result of the target vehicle according to the current first tracking result and the current second tracking result.
Specifically, the current first tracking result and the current second tracking result can be subjected to result level fusion to obtain the current target tracking result of the target vehicle. It will be appreciated that prior to fusing the current first tracking result and the current second tracking result, the current first tracking result and the current second tracking result need to be time and space synchronized to ensure co-dimensionality of the data. By way of example, the time synchronization of the first tracking result and the second tracking result may be achieved by a method of time hard synchronization or time soft synchronization. Further, after the current first tracking result and the current second tracking result are time-synchronized, the current first tracking result and the current second tracking result are converted into the same coordinate system, and space synchronization is completed. The conversion of the time hard synchronization or the time soft synchronization or the coordinate system is prior art, and specific steps are not repeated here.
Specifically, the current target tracking result can be understood as the result expansion of the current first tracking result and the current second tracking result, so that the characteristic information of the target vehicle is enriched. The current target tracking result may include a target category of the target vehicle, a current target position, a current target speed, a current target travel track, a current target heading angle, and the like.
S206, predicting the current driving dangerous behavior of the target vehicle according to the current target tracking result.
Wherein, the mapping relation among the driving dangerous behavior, the prediction condition and the tracking result of the vehicle can be preset. And predicting the current driving dangerous behavior of the target vehicle according to the mapping relation under the current target tracking result. For example, the mapping relationship among the driving risk behavior of the vehicle, the prediction condition, and the tracking result may be as shown in table 1.
TABLE 1
| Tracking results | Prediction condition | Predictive outcome (Driving hazard behavior) |
| Current target speed | The current target speed is less than the first speed threshold | Dangerous behavior of low speed driving |
| Current target speed | Current target speed > second speed threshold | Overspeed driving dangerous behavior |
| Current duration of driving | Current duration of driving > duration threshold | Dangerous behavior of fatigue driving |
Further, as can be seen from table 1, when the current target tracking result includes the current target speed and the current target speed is smaller than the first speed threshold, the target vehicle is predicted to be in a dangerous driving behavior of low speed driving, and at this time, the driving speed is too low, which causes road congestion and also easily causes a rear-end collision event.
When the current target tracking result comprises the current target speed and the current target speed is larger than the second speed threshold, the dangerous driving behavior of the target vehicle is predicted, at the moment, the driving speed is too high, and when the emergency is met, the vehicle is braked emergently, so that the vehicle overturns or overturns easily.
And predicting dangerous driving behaviors of the driver of the target vehicle for fatigue driving when the current target tracking result comprises the current continuous driving time length and the current continuous driving time length is larger than a time length threshold value.
The first speed threshold may be 30Km/h, or may be another value such as 40Km/h or 60Km/h, and may be specifically set in advance. For example, it may be preset according to a road scene. It is understood that driving conditions are different in different road scenes. For example, on an elevated road or an expressway, if a vehicle with a slow speed appears in the flow rate of the vehicle, the braking distance of the rear vehicle tends to be insufficient, which is liable to cause a rear-end collision event, and since the speed of the rear vehicle is relatively fast, the impact force on the vehicle to be rear-ended after the rear-end collision is relatively large, which causes a relatively large traffic accident. Preferably, the first speed threshold may be set to 60Km/h on an elevated road or an expressway to avoid traffic accidents due to too slow speed. Similarly, on town roads, the speed of the vehicle is generally relatively slow due to the large personnel concentration, so that the low-speed requirement can be properly reduced, but traffic jam is easily caused by the too low speed, so that a certain speed threshold value is also required to be set, and when the current target speed is smaller than the speed threshold value in the town road scene, the dangerous behavior of the target vehicle for low-speed driving is predicted. Preferably, the first speed threshold may be set to 30Km/h on town roads to avoid traffic congestion due to too slow speed.
Similarly, the second speed threshold may be 120Km/h, or may be another value such as 80Km/h or 60Km/h, and may be specifically set in advance. For example, it may be preset according to a road scene. For example, on an overhead road or an expressway, the driving speed is often high due to good road conditions, but the driving speed is too high, and when an emergency is encountered, the danger such as rear-end collision and rollover is easily caused by emergency braking, so that a relatively large traffic accident is caused. Therefore, it is necessary to set a certain high-speed threshold as a constraint. Preferably, on an overhead road or an expressway, the second speed threshold value can be set to 120Km/h, so as to avoid traffic accidents such as rear-end collision and rollover caused by too high speed. On town roads, because the people are dense, the time is long, and events such as traffic rules, ghost probes and the like are not observed, if the speed is too fast, pedestrians, non-motor vehicles or motor vehicles which are not observed in the traffic rules are encountered, or the ghost probes are encountered, the complete braking time is long, and collision with persons which are not observed in the traffic rules or ghost probes is easily caused, so that in order to reduce the occurrence of collision situations or reduce the collision degree, a certain high-speed threshold value is required to be set as constraint. Preferably, on town roads, the second speed threshold may be set to 60Km/h to reduce the occurrence of a collision or reduce the extent of the collision.
Further, based on the same principle, the above-mentioned time period threshold may be preset, for example, 4 hours, 5 hours, or 6 hours. Since the driver is tired and the fatigue driving is likely to cause driving accidents after long-time continuous driving, it is necessary to set a certain time period threshold as a constraint. Preferably, in this embodiment, the duration threshold may be 4 hours, and if the current duration is greater than 4 hours, the driver of the target vehicle is predicted to be in fatigue driving dangerous behavior.
And S208, sending target early warning information to the target object according to the current driving dangerous behavior.
The target object may refer to the target vehicle itself, or may refer to a traffic participant around the target vehicle, where the traffic participant may be a vehicle (other vehicle) having an information interaction function with the target vehicle, or the traffic participant may be a pedestrian or a non-vehicle having a communication device that can interact with the target vehicle. The target early warning information may be early warning prompt information corresponding to the current driving dangerous behavior.
In an implementation manner, step S208, sending the target early warning information to the target object according to the current driving dangerous behavior, may be specifically implemented according to the steps shown in fig. 3:
s2082, obtaining the corresponding relation among driving dangerous behaviors, early warning information and target objects.
S2084, according to the corresponding relation, early warning information corresponding to the predicted current driving dangerous behavior is sent to the target object.
The corresponding relation among the driving dangerous behavior, the early warning information and the target object can be preset and stored in a storage unit of the computer equipment, and the driving dangerous behavior, the early warning information and the target object can be directly acquired from the storage unit when needed.
Taking the target object as the target vehicle as an example, the corresponding relationship among the driving dangerous behavior, the early warning information and the target object may be the corresponding relationship shown in the following table 2.
TABLE 2
It can be understood that by sending the early warning information to the target vehicle, the driver of the target vehicle can timely learn the current driving dangerous behavior of the target vehicle, timely make driving decisions and improve driving safety.
Further, when the target object is another traffic participant around the target object, the driving dangerous behavior, the early warning information and the corresponding relationship of the target object may be preset. Taking the target object as an example of the adjacent vehicle running in front of or behind the target vehicle, the corresponding relationship among the driving dangerous behavior, the early warning information and the target object may be the corresponding relationship shown in the following table 3.
TABLE 3 Table 3
| Target object | Driving dangerous behavior | Early warning information |
| Front adjacent vehicle of target vehicle | Overspeed driving dangerous behavior | Rear overspeed driving, taking notice of avoiding |
| Rear adjacent vehicle of target vehicle | Dangerous behavior of low speed driving | Front vehicle running at low speed, attention to braking |
| Front adjacent vehicle of target vehicle | Dangerous behavior of fatigue driving | Fatigue driving of rear vehicle, attention avoidance |
| Rear adjacent vehicle of target vehicle | Dangerous behavior of fatigue driving | The front vehicle runs at a low speed, paying attention to avoidance |
It can be understood that by sending the early warning information to the adjacent vehicles in front of and behind the target vehicle, the adjacent vehicles in front of and behind the target vehicle can timely know the driving condition of the target vehicle, make driving decisions in advance, and improve driving safety.
It should be noted that the correspondence relationship between the target objects, the driving risk behaviors, and the early warning information listed in the foregoing tables 1 and 2 is merely an exemplary illustration, and in the implementation, the specific setting may be based on the prompt requirement, and the specific limitation is not herein made.
Further, according to the current target tracking result, the current driving dangerous behavior of the target vehicle is predicted, and the predicted result is only a predicted result corresponding to one predicted condition of the driving behavior of the target vehicle. In other prediction results, the predicted current driving behavior of the target vehicle may not belong to dangerous driving according to the current target tracking result, and at this time, the target information may be pushed to the target object according to the predicted current driving behavior of the target vehicle, where the pushed target information may be road information of a road on which the target vehicle is traveling. The road information may include static road information or dynamic road information. The static road information may include, but is not limited to, lane line information, lane marker information, roadside marker information, and the like, and the dynamic road information includes, but is not limited to, speed information, position information, lane change information, and the like of surrounding vehicles around the target vehicle.
It can be understood that the association relationship among the target object, the target information and the driving behavior can be preset, and after the current driving behavior of the target vehicle is predicted according to the current target tracking result, the target information pushed to the target object can be determined according to the association relationship. The specific association relationship may be preset based on requirements, and will not be specifically illustrated herein.
In implementation, the target early warning information or the target information described above may be sent to the target object in a voice form or may be sent to the target object in a text form. For example, when the target pre-warning information or the target information is transmitted to the target object in a voice form, the target object further has a receiver for receiving the voice information, and when the target pre-warning information or the target information is transmitted to the target object in a text form, the target object has a display screen capable of displaying the text information.
According to the driving behavior early warning method, the current first tracking result and the current second tracking result of the target vehicle are obtained after the target vehicle is tracked respectively by acquiring the image data and the point cloud data; determining a current target tracking result of the target vehicle according to the current first tracking result and the current second tracking result; predicting the current driving dangerous behavior of the target vehicle according to the current target tracking result; and sending target early warning information to the target object according to the current driving dangerous behavior. According to the method, the current target tracking result of the target vehicle can be determined by combining the tracking result of the image data on the target vehicle and the tracking result of the point cloud data on the target vehicle, and the current driving dangerous behavior of the target vehicle is predicted based on the current target tracking result. According to the scheme, the target early warning information is further sent to the target object according to the current driving dangerous behavior. The dangerous driving behavior of the target vehicle can be correspondingly warned and reminded, and driving safety is improved.
In another embodiment, another driving behavior early warning method is provided, and based on the above embodiment, as shown in fig. 4, the step S206 may include the following steps:
s302, determining the current variable pass number of the target vehicle according to the current target running track.
In one example, during the driving of the target vehicle, whether the target vehicle changes lanes at the current moment can be determined in real time according to the track line direction of the current target driving track. It can be understood that when the vehicle is traveling on the same lane, the vehicle is generally traveling straight, and when the current position of the vehicle is in an S route with the previous position, it is indicated that the vehicle is performing lane change, and the current lane change of the vehicle can be determined by adding 1 to the recorded lane change of the previous vehicle.
S304, predicting the current driving dangerous behavior of the target vehicle according to the current transition number.
Specifically, a variable-pass threshold may be set, and when the current variable-pass number reaches the variable-pass threshold, the current driving behavior of the target vehicle is predicted to be a frequent variable-pass driving dangerous behavior. The variable pass number threshold may be 4 times, 5 times, 6 times or other times, and the specific times may be set according to actual requirements, which is not specifically limited herein.
Further, on the basis of the above embodiment, based on the number of variation passes, the map relationship between the driving risk behavior, the prediction condition, and the tracking result of the vehicle shown in table 4 may be constructed on the basis of table 1.
TABLE 4 Table 4
Further, as can be seen from table 4, when the tracking result includes the current lane change number and the current lane change number reaches the threshold value of the lane change number, the lane change of the target vehicle is predicted to be frequent during the driving process, and the target vehicle belongs to the frequent lane change driving dangerous behavior. It will be appreciated that due to frequent lane changes, driving disturbances may be imparted to surrounding vehicles of the target vehicle, and a scratch event may easily occur. Therefore, it is possible to send the target early warning information to the target object (the reference object of the target object may refer to the description of the above embodiment) when the current driving behavior of the target vehicle is predicted to be the frequent lane change driving dangerous behavior. In this scenario, the target early warning information may be information such as frequent lane change driving prompts or attention avoidance prompts.
In a specific implementation, the determining that the lane change behavior occurs at the current time of the target vehicle by determining that the driving route of the target vehicle is the "S" route is only a limited scheme, and in other embodiments, as shown in fig. 5, step S302, determining the current lane change number of the target vehicle according to the current target driving track may further include the following steps:
s402, acquiring lane lines of a target area.
In a specific implementation, lane lines of the target area may be acquired on a high-precision map. The target area is an area determined by the current perception range of the road side equipment.
S404, determining the number of the current intersection points of the current target running track and the lane lines.
S406, determining the number of the current intersection points of the current target running track and the lane lines as the current variable number of the target vehicle.
It can be understood that if the lane change occurs in the driving process of the target vehicle, the driving track line inevitably intersects with the lane line, and an intersection point exists between the driving track line and the lane line, so that the number of the current intersection points of the current target driving track and the lane line can be determined first, and then the number of the current intersection points of the current target driving track and the lane line can be determined as the current lane change number of the target vehicle. The computer equipment can record lane change data each time in real time before the current moment, and the number of the current intersection points of the current target running track of the target vehicle and the lane lines is obtained by directly adding 1 on the basis of the number of the previous intersection points when judging that the intersection points exist between the current target running track and the lane lines as the number of the previous lane changes.
The current dangerous driving behavior of the target vehicle is predicted through the current lane changing number, and early warning reminding can be given when the vehicle frequently changes lanes, so that the driving safety is improved.
In another embodiment, another driving behavior early warning method is provided, and based on the above embodiment, as shown in fig. 6, the step S206 may include the following steps: :
S502, surrounding vehicle information of the target vehicle and current lane change points and reference lane change points of the target vehicle are acquired.
It will be appreciated that the target vehicle may change track multiple times during the whole current target driving track, i.e. there are multiple track changing points, and the data having a relatively large influence on the current target tracking result is generally one track changing point before the current track changing point. In this embodiment, the reference lane change point is an adjacent lane change point of the target vehicle before the current lane change point.
And S504, if the current lane change point and the reference lane change point are on the same lane line, acquiring the reference overtaking times and surrounding vehicle information of the target vehicle.
S506, determining the current overtaking times of the target vehicle according to the surrounding vehicle information and the reference overtaking times.
Specifically, if the current lane change point and the reference lane change point are on the same lane line, the target vehicle is described to return to the original lane before lane change again after lane change. After the lane change, the vehicle returns to the original lane, and the general description of the vehicle overtaking lane is provided. At this time, the reference overtaking times and the surrounding vehicle information of the target vehicle can be acquired, whether the target vehicle overtakes or not is determined according to the surrounding vehicle information of the target vehicle, and the current overtaking times are determined according to the reference overtaking times. In one example, as shown in fig. 7, step S506 may include the following steps:
S602, if vehicle information between the current lane change point and the reference lane change point exists in surrounding vehicle information, determining that the target vehicle has overtaking behaviors at the current lane change point.
It can be understood that if there is vehicle information between the current lane change point and the reference lane change point in the surrounding vehicle information, it is indicated that the target vehicle returns to the original lane after lane change in order to overrun the vehicle, and at this time, it is determined that the target vehicle has overtaking behavior at the current lane change point. Further, if there is no vehicle information located between the current lane change point and the reference lane change point in the surrounding vehicle information, it is indicated that the target vehicle may only want to travel in a lane change, and at this time, the target vehicle is not considered to have overtaking behaviors.
S604, the reference overtaking times are added with 1 to determine the current overtaking times of the target vehicle.
When the computer equipment determines that the target vehicle overtakes each time, the overtaking times of each time are updated once to be used as the reference overtaking times of the next overtaking time, and the reference overtaking times can be understood as the overtaking times corresponding to the target vehicle at the reference lane change point.
S508, predicting the current driving dangerous behavior of the target vehicle according to the current overtaking times.
Specifically, the threshold of the number of overtaking times may be preset, and when the current number of overtaking times reaches the threshold of the number of overtaking times, the current driving behavior of the target vehicle is predicted to be a frequent overtaking driving dangerous behavior.
In one embodiment, based on the above example, based on the current number of overtakes, the map relationship between the driving risk behavior, the prediction condition, and the tracking result of the vehicle shown in table 5 may be constructed on the basis of table 1 or table 4 (in this embodiment, table 5 is constructed on the basis of table 4).
TABLE 4 Table 4
Further, based on the table 5, when the tracking result includes the current overtaking frequency and the current overtaking frequency reaches the overtaking frequency threshold, frequent overtaking of the target vehicle in the running process is predicted, and the target vehicle belongs to frequent overtaking driving dangerous behaviors. It will be appreciated that due to frequent overtaking, driving disturbances may be imparted to surrounding vehicles of the target vehicle, and a scratch event may easily occur. In addition, in the overtaking process, the overtaking speed is often required to be relatively high, and the higher driving speed brings a certain driving risk for the target vehicle to return to the original lane, so that when the current driving behavior of the target vehicle is predicted to be the frequent overtaking driving dangerous behavior, the target early warning information can be sent to the target object (the reference object of the target object can refer to the description of the embodiment). In this scenario, the target early warning information may be information such as frequent overtaking driving prompts, or attention avoidance prompts.
The current dangerous driving behavior of the target vehicle is predicted through the current overtaking times, and early warning reminding can be given when the vehicle overtakes frequently, so that the driving safety is improved.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a driving behavior early warning device for realizing the driving behavior early warning method. The implementation scheme of the solution to the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitation in the embodiments of the driving behavior early warning device provided below may refer to the limitation of the driving behavior early warning method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 8, there is provided a driving behavior early warning apparatus including: the system comprises an acquisition module, a tracking result determining module, a prediction module and an early warning module, wherein:
the acquisition module is used for acquiring a current first tracking result and a current second tracking result of the target vehicle, which are obtained after the target vehicle is tracked by the image data and the point cloud data respectively.
And the tracking result determining module is used for determining the current target tracking result of the target vehicle according to the current first tracking result and the current second tracking result.
And the prediction module is used for predicting the current driving dangerous behavior of the target vehicle according to the current target tracking result.
And the early warning module is used for sending target early warning information to the target object according to the current driving dangerous behavior.
In another embodiment, another driving behavior early warning device is provided, and on the basis of the above embodiment, the prediction module may include a variable-number-of-times determining unit and a first prediction unit, where:
and the variable pass number determining unit is used for determining the current variable pass number of the target vehicle according to the current target running track when the current target tracking result comprises the current target running track.
And the first prediction unit is used for predicting the current driving dangerous behavior of the target vehicle according to the current variable pass number.
In another embodiment, another driving behavior early warning device is provided, and on the basis of the above embodiment, the variable-number-of-passes determining unit may further include a lane-line acquiring subunit, an intersection number determining subunit, and a variable-number-of-passes determining subunit, where,
The lane line acquisition subunit is used for acquiring lane lines of a target area, wherein the target area is an area determined by the current perception range of the road side equipment.
And the intersection point number determining subunit is used for determining the current intersection point number of the current target running track and the lane line.
And the variable-pass number determining subunit is used for determining the number of the current intersection points of the current target running track and the lane lines as the current variable-pass number of the target vehicle.
In another embodiment, another driving behavior early warning device is provided, and on the basis of the above embodiment, the prediction module may further include a lane change point determining unit, a first obtaining unit, a number of overtaking times determining unit, and a second prediction unit, where,
The lane change point determining unit is used for obtaining surrounding vehicle information of the target vehicle, a current lane change point of the target vehicle and a reference lane change point, wherein the reference lane change point is an adjacent lane change point of the target vehicle before the current lane change point.
The first acquisition unit is used for acquiring the reference overtaking times and surrounding vehicle information of the target vehicle when the current lane change point and the reference lane change point are on the same lane line, wherein the reference overtaking times are corresponding overtaking times of the target vehicle at the reference lane change point.
And the overtaking frequency determining unit is used for determining the current overtaking frequency of the target vehicle according to the surrounding vehicle information and the reference overtaking frequency.
And the second prediction unit is used for predicting the current driving dangerous behavior of the target vehicle according to the current overtaking times.
In another embodiment, another driving behavior early warning device is provided, and on the basis of the above embodiment, the overtaking number determining unit further includes an overtaking behavior determining subunit and an overtaking number determining subunit, wherein,
And the overtaking behavior determination subunit is used for determining that the target vehicle has overtaking behaviors at the current lane change point when the vehicle information between the current lane change point and the reference lane change point exists in the surrounding vehicle information.
And the overtaking frequency subunit is used for adding 1 to the reference overtaking frequency to determine the current overtaking frequency of the target vehicle.
The above-mentioned driving behavior early warning device may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, taking the computer device as a terminal as an example, and the internal structure diagram thereof may be as shown in fig. 9. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a vehicle behavior prediction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
Acquiring current first tracking results and current second tracking results of the target vehicle, which are obtained after the target vehicle is tracked by the image data and the point cloud data respectively; determining a current target tracking result of the target vehicle according to the current first tracking result and the current second tracking result; predicting the current driving dangerous behavior of the target vehicle according to the current target tracking result; and sending target early warning information to the target object according to the current driving dangerous behavior.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining the current variable pass number of the target vehicle according to the current target running track;
and predicting the current driving dangerous behavior of the target vehicle according to the current variable pass number.
In one embodiment, the processor when executing the computer program further performs the steps of:
Acquiring a lane line of a target area, wherein the target area is an area determined by the current perception range of road side equipment; determining the number of current intersection points of the current target running track and the lane line; and determining the number of the current intersection points of the current target running track and the lane lines as the current variable pass number of the target vehicle.
In one embodiment, the processor when executing the computer program further performs the steps of:
Acquiring surrounding vehicle information of a target vehicle, and a current lane change point and a reference lane change point of the target vehicle, wherein the reference lane change point is an adjacent lane change point of the target vehicle before the current lane change point; if the current lane change point and the reference lane change point are on the same lane line, acquiring the reference overtaking times and surrounding vehicle information of the target vehicle, wherein the reference overtaking times are corresponding overtaking times of the target vehicle at the reference lane change point; determining the current overtaking times of the target vehicle according to the surrounding vehicle information and the reference overtaking times; and predicting the current driving dangerous behavior of the target vehicle according to the current overtaking times.
In one embodiment, the processor when executing the computer program further performs the steps of:
If the surrounding vehicle information contains the vehicle information between the current lane change point and the reference lane change point, determining that the target vehicle has overtaking behaviors at the current lane change point; and adding 1 to the reference overtaking number to determine the current overtaking number of the target vehicle.
In one embodiment, the processor when executing the computer program further performs the steps of:
Acquiring driving dangerous behaviors, early warning information and corresponding relation of a target object; and sending early warning information corresponding to the predicted current driving dangerous behavior to the target object according to the corresponding relation.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
Acquiring current first tracking results and current second tracking results of the target vehicle, which are obtained after the target vehicle is tracked by the image data and the point cloud data respectively; determining a current target tracking result of the target vehicle according to the current first tracking result and the current second tracking result; predicting the current driving dangerous behavior of the target vehicle according to the current target tracking result; and sending target early warning information to the target object according to the current driving dangerous behavior.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Determining the current variable pass number of the target vehicle according to the current target running track; and predicting the current driving dangerous behavior of the target vehicle according to the current variable pass number.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring a lane line of a target area, wherein the target area is an area determined by the current perception range of road side equipment; determining the number of current intersection points of the current target running track and the lane line; and determining the number of the current intersection points of the current target running track and the lane lines as the current variable pass number of the target vehicle.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring surrounding vehicle information of a target vehicle, and a current lane change point and a reference lane change point of the target vehicle, wherein the reference lane change point is an adjacent lane change point of the target vehicle before the current lane change point;
If the current lane change point and the reference lane change point are on the same lane line, acquiring the reference overtaking times and surrounding vehicle information of the target vehicle, wherein the reference overtaking times are corresponding overtaking times of the target vehicle at the reference lane change point; determining the current overtaking times of the target vehicle according to the surrounding vehicle information and the reference overtaking times; and predicting the current driving dangerous behavior of the target vehicle according to the current overtaking times.
In one embodiment, the computer program when executed by the processor further performs the steps of:
If the surrounding vehicle information contains the vehicle information between the current lane change point and the reference lane change point, determining that the target vehicle has overtaking behaviors at the current lane change point; and adding 1 to the reference overtaking number to determine the current overtaking number of the target vehicle.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring driving dangerous behaviors, early warning information and corresponding relation of a target object; and sending early warning information corresponding to the predicted current driving dangerous behavior to the target object according to the corresponding relation.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
A current first tracking result and a current second tracking result; determining a current target tracking result of the target vehicle according to the current first tracking result and the current second tracking result; predicting the current driving dangerous behavior of the target vehicle according to the current target tracking result; and sending target early warning information to the target object according to the current driving dangerous behavior.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Determining the current variable pass number of the target vehicle according to the current target running track; and predicting the current driving dangerous behavior of the target vehicle according to the current variable pass number.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring a lane line of a target area, wherein the target area is an area determined by the current perception range of road side equipment; determining the number of current intersection points of the current target running track and the lane line; and determining the number of the current intersection points of the current target running track and the lane lines as the current variable pass number of the target vehicle.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring surrounding vehicle information of a target vehicle, and a current lane change point and a reference lane change point of the target vehicle, wherein the reference lane change point is an adjacent lane change point of the target vehicle before the current lane change point;
If the current lane change point and the reference lane change point are on the same lane line, acquiring the reference overtaking times and surrounding vehicle information of the target vehicle, wherein the reference overtaking times are corresponding overtaking times of the target vehicle at the reference lane change point; determining the current overtaking times of the target vehicle according to the surrounding vehicle information and the reference overtaking times; and predicting the current driving dangerous behavior of the target vehicle according to the current overtaking times.
In one embodiment, the computer program when executed by the processor further performs the steps of:
If the surrounding vehicle information contains the vehicle information between the current lane change point and the reference lane change point, determining that the target vehicle has overtaking behaviors at the current lane change point; and adding 1 to the reference overtaking number to determine the current overtaking number of the target vehicle.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring driving dangerous behaviors, early warning information and corresponding relation of a target object; and sending early warning information corresponding to the predicted current driving dangerous behavior to the target object according to the corresponding relation.
The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.