Vehicle data management method, device, equipment and medium

Abstract

The invention discloses a vehicle data management method and device, equipment and a medium, and relates to the technical field of intelligent driving, and the method comprises the steps: updating the historical data, stored in a preset memory pool, of each vehicle through the current frame data, detected by a vehicle sensor, of each surrounding vehicle; judging whether a target vehicle losing data exists in a preset memory pool or not; if the target vehicle losing the data exists, whether the target vehicle is located in a target position area constructed with the vehicle as the center or not is judged; and if the target vehicle is located in the target position area, predicting state information of the current frame according to the previous frame data of the target vehicle, and taking the state information as the current frame data of the target vehicle. According to the method, the prediction information is added to the target vehicle which is suddenly lost in the target position area and is stored instead of immediately releasing the data of the target vehicle, so that the dangerous behavior caused by the fact that the NOA executes the lane changing action due to the fact that the sensor suddenly loses the target information due to a blind area is avoided, and the safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a vehicle data management method, device, equipment and medium. Background Art

[0002] Currently, many smart driving vehicles are equipped with the NOA (Navigate on Autopilot) function, which enables autonomous on- and off-ramps.

[0003] However, when the current intelligent driving NOA requests a lane change, due to the limitations of the corner radar's blind spot recognition conditions, if the target vehicle on the current lane change side is aligned with the vehicle itself, the corner radar may suddenly lose the information of the target vehicle. At this time, the functional layer mistakenly believes that there is no obstacle on the lane change side and can execute the lane change action, which may lead to an accident.

[0004] In summary, how to prevent the sensor from suddenly losing target information due to blind spots, resulting in dangerous behaviors caused by NOA lane changing, so as to improve the safety of lane changing is a problem that needs to be solved. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a vehicle data management method, device, equipment and medium, which can prevent the sensor from suddenly losing target information due to blind spots, resulting in dangerous behaviors caused by NOA lane change actions, so as to improve the safety of lane change. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a vehicle data management method, comprising:

[0007] The historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor;

[0008] Determine whether there is a target vehicle with lost data in the preset memory pool;

[0009] If there is a target vehicle with missing data, determining whether the target vehicle is located in a target location area constructed with the vehicle as the center;

[0010] If the target vehicle is located in the target position area, the state information of the current frame is predicted according to the previous frame data of the target vehicle, and the state information is used as the current frame data of the target vehicle.

[0011] Optionally, each vehicle in the preset memory pool is provided with an attribute parameter for characterizing the total number of frames of data loss, and before the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor, the method further includes:

[0012] Determine whether the preset memory pool is empty;

[0013] If the preset memory pool is not empty, the attribute parameter corresponding to each vehicle in the preset memory pool is incremented by 1, and the historical data in the preset memory pool that meets the preset clearing condition is cleared, and the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor;

[0014] If the preset memory pool is empty, the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor.

[0015] Optionally, the updating of the historical data of each vehicle stored in a preset memory pool by using the current frame data of each surrounding vehicle detected by the vehicle sensor includes:

[0016] Acquire current frame data of each surrounding vehicle detected by the vehicle sensor; wherein the current frame data includes a set of identification numbers and current driving states of each surrounding vehicle;

[0017] If the first identification number in the identification number set exists in the preset memory pool, the historical driving state corresponding to the first identification number in the preset memory pool is updated using the current driving state corresponding to the first identification number, and the attribute parameter of the vehicle corresponding to the first identification number is assigned to 0;

[0018] If the second identification number in the identification number set does not exist in the preset memory pool, the second identification number and the corresponding current driving status are added to the preset memory pool, and the attribute parameter of the vehicle corresponding to the second identification number is assigned to 0.

[0019] Optionally, the determining whether there is a target vehicle with lost data in the preset memory pool includes:

[0020] Determine whether there is a vehicle with the attribute parameter greater than 0 in the preset memory pool;

[0021] If so, the vehicle whose attribute parameter is greater than 0 is determined as the target vehicle that has lost the current frame data.

[0022] Optionally, clearing the historical data in the preset memory pool that meets a preset clearing condition includes:

[0023] Traversing the attribute parameters corresponding to each vehicle in the preset memory pool, and determining a set of vehicles whose attribute parameters are greater than 1;

[0024] The historical data of the vehicles in the vehicle set that meet the preset clearing condition are cleared.

[0025] Optionally, clearing the historical data of the vehicles in the vehicle set that meet a preset clearing condition includes:

[0026] If any vehicle in the vehicle set is not located in the target location area, clearing the historical data of any vehicle;

[0027] Or, traverse the current frame data of each surrounding vehicle detected by the vehicle sensor, and if it is determined based on the current frame data that there is a vehicle among the surrounding vehicles that matches any vehicle in the vehicle set, clear the historical data of any vehicle;

[0028] Alternatively, the relative speed between the speed of the last frame of data of each vehicle in the vehicle set before being lost and the speed of the vehicle itself is determined respectively, and a maximum storage time value corresponding to the relative speed is determined; if the attribute parameter of any vehicle in the vehicle set is greater than the maximum storage time value, the historical data of any vehicle is cleared.

[0029] Optionally, determining, based on the current frame data, that there is a vehicle among the surrounding vehicles that matches any vehicle in the vehicle set includes:

[0030] For any vehicle in the vehicle set, if there is a vehicle among the surrounding vehicles whose lateral distance to the any vehicle is less than a first preset value and whose longitudinal distance to the any vehicle is less than a second preset value, it is determined that there is a vehicle among the surrounding vehicles that matches the any vehicle.

[0031] In a second aspect, the present application discloses a vehicle data management device, comprising:

[0032] An updating module, used to update the historical data of each vehicle stored in a preset memory pool using the current frame data of each surrounding vehicle detected by the vehicle sensor;

[0033] A first judgment module is used to judge whether there is a target vehicle with lost data in the preset memory pool;

[0034] A second judgment module is used to judge whether the target vehicle is located in a target position area constructed with the vehicle as the center if there is a target vehicle with lost data;

[0035] The prediction module is used to predict the state information of the current frame according to the previous frame data of the target vehicle if the target vehicle is located in the target position area, and use the state information as the current frame data of the target vehicle.

[0036] In a third aspect, the present application discloses an electronic device, comprising:

[0037] Memory, used to store computer programs;

[0038] The processor is used to execute the computer program to implement the steps of the vehicle data management method disclosed above.

[0039] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the vehicle data management method disclosed above are implemented.

[0040] It can be seen that the present application uses the current frame data of the surrounding vehicles detected by the vehicle's sensor to update the historical data of each vehicle stored in a preset memory pool; determines whether there is a target vehicle with lost data in the preset memory pool; if there is a target vehicle with lost data, determines whether the target vehicle is located in a target position area constructed with the vehicle as the center; if it is located in the target position area, predicts the status information of the current frame based on the previous frame data of the target vehicle, and uses the status information as the current frame data of the target vehicle.

[0041] Beneficial effects: A preset memory pool is provided in the present application to store the data of each vehicle. When the vehicle sensor detects the current frame data of the surrounding vehicles, the historical data in the preset memory pool needs to be updated in real time using the current frame data. After completing the update of the memory pool, it is first necessary to determine whether there is a target vehicle that has lost the current frame data in the preset memory pool. If there is a target vehicle that has lost data, it is further determined whether the target vehicle is located in the target position area constructed with the vehicle as the center. If it is located in the target position area, the state information of the current frame is predicted based on the previous frame data of the target vehicle, and the state information is used as the current frame data of the target vehicle. That is, the present application predicts the state of the target vehicle that is suddenly lost in the target position area, and stores the predicted state as its current frame data, instead of immediately releasing the data of the target vehicle, thereby avoiding the sensor suddenly losing the target information due to the blind spot, resulting in dangerous behavior caused by NOA executing the lane change action, and improving the safety of lane change. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0043] Figure 1 A flow chart of a vehicle data management method disclosed in this application;

[0044] Figure 2 A flow chart of a specific vehicle data management method disclosed in this application;

[0045] Figure 3 This is a display diagram of the first type of vehicle data disclosed in this application;

[0046] Figure 4 A display diagram of the second type of vehicle data disclosed in this application;

[0047] Figure 5 This is a display diagram of the third type of vehicle data disclosed in this application;

[0048] Figure 6 This is a schematic diagram of the structure of a vehicle data management device disclosed in this application;

[0049] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] When the current intelligent driving NOA requests a lane change, due to the conditional limitations of the corner radar recognition blind spot, if the target vehicle on the current lane change side is aligned with the vehicle, the corner radar may suddenly lose the information of the target vehicle. At this time, the functional layer mistakenly believes that there is no obstacle on the lane change side and can execute the lane change action, thereby causing an accident. To this end, the embodiment of the present application discloses a vehicle data management method, device, equipment and medium, which can prevent the sensor from suddenly losing target information due to the blind spot, resulting in dangerous behavior caused by NOA executing the lane change action, so as to improve the safety of lane change.

[0052] See also Figure 1 and Figure 2 As shown, the embodiment of the present application discloses a vehicle data management method, the method comprising:

[0053] Step S11: using the current frame data of surrounding vehicles detected by the vehicle sensor to update the historical data of each vehicle stored in the preset memory pool.

[0054] In this embodiment, it should be pointed out that multiple sensors are installed in front and rear of the vehicle body to detect the distance, speed and other information of the front and rear vehicles in real time to realize adaptive cruise control, automatic emergency braking and other functions. In order to store the surrounding vehicle data detected by the sensor, the present application is provided with a preset memory pool. Therefore, when the vehicle sensor detects the current frame data of the surrounding vehicles, it is necessary to use the current frame data in real time to update the historical data in the preset memory pool.

[0055] Furthermore, each vehicle in the preset memory pool is provided with an attribute parameter for characterizing the total number of frames of data loss. Before the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle's sensor, it also includes: determining whether the preset memory pool is empty; if the preset memory pool is not empty, adding 1 to the attribute parameter corresponding to each vehicle in the preset memory pool, clearing the historical data in the preset memory pool that meets the preset clearing condition, and updating the historical data of each vehicle stored in the preset memory pool using the current frame data of each surrounding vehicle detected by the vehicle's sensor; if the preset memory pool is empty, updating the historical data of each vehicle stored in the preset memory pool using the current frame data of each surrounding vehicle detected by the vehicle's sensor.

[0056] That is, in the embodiment of the present application, each vehicle is provided with an attribute parameter lossCount for characterizing the total number of frames of data loss. This attribute parameter will be updated with each data collected by the vehicle sensor, including update operations such as clearing and accumulation. Each time before the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of the surrounding vehicles detected by the vehicle sensor, it is necessary to determine whether the preset memory pool is empty, that is, to determine whether there is data stored in the preset memory pool. Among them, there are usually two situations in which the preset memory pool is empty. One is that the vehicle has just started, and the sensor has just started working, so there is no data stored in the preset memory pool; the other is that the vehicle has been driving in an open area for a long time, and because there are no vehicles around, there is no data stored in the preset memory pool.

[0057] In a specific implementation, if the preset memory pool is not empty, the preset memory pool is traversed, and the attribute parameter lossCount corresponding to each vehicle in the preset memory pool is added by 1, that is, it is first assumed that the data of each vehicle in the preset memory pool is in a lost state in the current frame. Then, the historical data in the preset memory pool that meets the preset clearing condition is cleared, and then the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of the surrounding vehicles detected by the vehicle sensor. By clearing the historical data in the preset memory pool that meets the preset clearing condition, storage space can be saved and the storage of some useless data can be avoided.

[0058] In another specific implementation, if the preset memory pool is empty, there is no data to be cleared in the preset memory pool, so the historical data of each vehicle stored in the preset memory pool is directly updated using the current frame data of the surrounding vehicles detected by the vehicle sensor.

[0059] In a specific embodiment, the above-mentioned use of current frame data of surrounding vehicles detected by the vehicle's own sensor to update the historical data of each vehicle stored in a preset memory pool includes: obtaining current frame data of surrounding vehicles detected by the vehicle's own sensor; wherein the current frame data includes a set of identification numbers and current driving status of the surrounding vehicles; if the preset memory pool contains a first identification number in the identification number set, the historical driving status corresponding to the first identification number in the preset memory pool is updated using the current driving status corresponding to the first identification number, and the attribute parameter of the vehicle corresponding to the first identification number is assigned to 0; if the preset memory pool does not contain a second identification number in the identification number set, the second identification number and the corresponding current driving status are added to the preset memory pool, and the attribute parameter of the vehicle corresponding to the second identification number is assigned to 0.

[0060] In this embodiment, the current frame data of the surrounding vehicles detected by the vehicle sensor is first obtained. The current frame data specifically includes the identification number set of the surrounding vehicles and the current driving status. It can be understood that each time the sensor detects the surrounding vehicle data, it will assign an identification number to it. The assignment rule is: if the currently detected vehicle has not appeared in the previous frame, a random identification number is generated and assigned; if the currently detected vehicle has appeared in the previous frame, the identification number of the previous frame is directly used for assignment. It should be pointed out that if the vehicle has appeared in the previous data, but a part of the data has been lost in the middle, but it reappears, it is also necessary to use the randomly generated identification number for assignment. The current driving status specifically includes the speed information and position information of the vehicle.

[0061] Furthermore, the preset memory pool is traversed. If the first identification number in the identification number set exists in the preset memory pool, it means that the previous frame data of the corresponding vehicle has been saved in the preset memory pool, and it also means that the data of the vehicle has not been lost in the current frame. Therefore, the current driving state corresponding to the first identification number is used to update the historical driving state corresponding to the first identification number in the preset memory pool, and the attribute parameter lossCount of the vehicle corresponding to the first identification number is assigned to 0. In addition, if the second identification number in the identification number set does not exist in the preset memory pool, it means that the previous frame data of the vehicle does not exist in the preset memory pool, and the vehicle is a target newly added in the sensor field of view. Therefore, in this case, the second identification number and the corresponding current driving state are added to the preset memory pool, and the attribute parameter lossCount of the vehicle corresponding to the second identification number is also assigned to 0.

[0062] In addition, the embodiment of the present application also sets an attribute importantValue for characterizing whether the vehicle is located in the target position area. It can be understood that the present embodiment divides the data in the preset memory pool into two areas according to the horizontal and vertical coordinates of the vehicle, namely, the key concern area and the non-key concern area. For example, the area centered on the vehicle, 10m in front and behind, and 8m in left and right can be regarded as the key concern area, that is, the above-mentioned target position area. If the horizontal and vertical coordinates (dx, dy) of a certain vehicle are within the key concern area, the target is assigned an attribute importantValue=1, otherwise importantValue=0. It should be pointed out that the specific range of the above-mentioned target position area is calibrable and is not limited to the 10m and 8m mentioned in this example. In addition, the target position area can also be a circular area.

[0063] Therefore, in the process of updating the historical data of each vehicle stored in the preset memory pool using the current frame data, in addition to updating the lossCount attribute, the importantValue attribute also needs to be updated. Therefore, while assigning the attribute parameter lossCount of the vehicle corresponding to the first identification number to 0, it is also necessary to determine whether it is located in the target position area based on the horizontal and vertical coordinates of the vehicle corresponding to the first identification number, and update the corresponding importantValue attribute; similarly, while assigning the attribute parameter lossCount of the vehicle corresponding to the second identification number to 0, it is also necessary to determine whether it is located in the target position area based on the horizontal and vertical coordinates of the vehicle corresponding to the second identification number, and update the corresponding importantValue attribute.

[0064] Step S12: Determine whether there is a target vehicle with lost data in the preset memory pool.

[0065] In this embodiment, after the memory pool is updated, it is first necessary to determine whether there is a target vehicle that has lost the current frame data in the preset memory pool.

[0066] Specifically, the above-mentioned determination of whether there is a target vehicle with lost data in the preset memory pool includes: determining whether there is a vehicle with the attribute parameter greater than 0 in the preset memory pool; if so, determining the vehicle with the attribute parameter greater than 0 as a target vehicle that has lost the current frame data. It can be understood that, from the foregoing content, when the historical data in the preset memory pool is updated using the current frame data in each cycle, if the newly-incoming identification number can be traversed in the preset memory pool, lossCount is assigned to 0; if the target does not exist in the memory pool, the target is considered to be a new target, and lossCount is also assigned to 0. Therefore, if there is still a vehicle with the attribute parameter lossCount greater than 0 in the preset memory pool at this time, it means that the vehicle is a target vehicle that has lost the current frame data.

[0067] Step S13: If there is a target vehicle with missing data, it is determined whether the target vehicle is located within a target location area constructed with the vehicle as the center.

[0068] In this embodiment, if there is a target vehicle with missing data, it is further determined whether the target vehicle is located in the target location area constructed with the vehicle as the center. Specifically, if the importantValue attribute of the target vehicle is 1, it is determined that the target vehicle is located in the target location area constructed with the vehicle as the center.

[0069] Step S14: If the target vehicle is located in the target position area, predict the state information of the current frame according to the previous frame data of the target vehicle, and use the state information as the current frame data of the target vehicle.

[0070] In this embodiment, if the target vehicle is located in the target position area, the state information of the current frame is predicted based on the previous frame data of the target vehicle, and the state information is used as the current frame data of the target vehicle. That is, the present application predicts the state of the target vehicle that is suddenly lost in the target position area, and stores the predicted state as its current frame data, rather than immediately releasing the data of the target vehicle, thereby avoiding the dangerous behavior caused by NOA executing the lane change action due to the sudden loss of target information by the sensor due to the blind spot, and improving the safety of lane change.

[0071] The embodiment of the present application sets a distance around the vehicle (which can be calibrated) as the key concern area, and adds prediction information for the target that is suddenly lost in the key concern area, that is, the state of the target vehicle with importantValue=1 and lossCount greater than 0 in the preset memory pool is predicted. The specific prediction method is that, assuming that the target is moving at a constant speed, the position information of the current frame can be predicted based on the previous frame data of the target vehicle:

[0072] ;

[0073] Where z= is the previous frame data of the target vehicle, x and y are the horizontal and vertical coordinates of the previous frame, and v x and v y is the speed in the horizontal and vertical directions of the previous frame, a x and a y is the acceleration in the horizontal and vertical directions of the previous frame, and is the predicted horizontal and vertical coordinate position of the current frame.

[0074] As mentioned above, each time before the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor, if the preset memory pool is not empty, the historical data in the preset memory pool that meets the preset clearing condition needs to be cleared to avoid storing some useless data. In a specific implementation, the predicted data is mainly cleared. It can be understood that since the predicted target is a virtual target, it cannot exist for a long time and needs to be cleared at an appropriate time. Therefore, the embodiment of the present application needs to check whether there is an inappropriate predicted target before storing the current frame data.

[0075] Specifically, the above-mentioned clearing process of the historical data in the preset memory pool that meets the preset clearing condition includes: traversing the attribute parameters corresponding to each vehicle in the preset memory pool, and determining the vehicle set whose attribute parameters are greater than 1; clearing the historical data of the vehicles in the vehicle set that meet the preset clearing condition. It can be seen from the foregoing that before updating the data in the preset memory pool, the embodiment of the present application first adds 1 to the attribute parameter lossCount corresponding to each vehicle in the preset memory pool. Therefore, if there is still a vehicle with an attribute parameter lossCount greater than 1 in the preset memory pool at this time, it is said that the vehicle has lost at least two frames of data in succession.

[0076] Therefore, this application needs to traverse the attribute parameters corresponding to each vehicle in the preset memory pool, determine the vehicle set whose attribute parameters are greater than 1, and then clear the historical data of the vehicles in the vehicle set that meet the preset clearing conditions. That is, among the data of these vehicles that have not been detected for a long time, the historical data of the vehicles that meet the preset clearing conditions are cleared.

[0077] Specifically, the above-mentioned clearing of historical data of vehicles in the vehicle set that meet the preset clearing conditions includes: if any vehicle in the vehicle set is not located in the target location area, clearing the historical data of any vehicle; or, traversing the current frame data of the surrounding vehicles detected by the vehicle sensor, if it is determined based on the current frame data that there is a vehicle matching any vehicle in the vehicle set among the surrounding vehicles, clearing the historical data of any vehicle; or, respectively determining the relative speed between the speed of the last frame of data of each vehicle in the vehicle set before it is lost and the speed of the vehicle, and determining the maximum storage time value corresponding to the relative speed, if the attribute parameter of any vehicle in the vehicle set is greater than the maximum storage time value, clearing the historical data of any vehicle.

[0078] That is, the embodiment of the present application specifically discloses three clearing conditions:

[0079] The first one is that if the horizontal and vertical coordinate positions of any vehicle in the vehicle set have exceeded the target position area, the historical data of any vehicle is cleared.

[0080] The second is to traverse the current frame data of the surrounding vehicles detected by the vehicle sensor. If it is determined based on the current frame data that there is a vehicle matching any vehicle in the vehicle set among the surrounding vehicles, it means that the target data actually detected by the sensor is found near the any vehicle, so the historical data of the predicted any vehicle is cleared. In a specific embodiment, the above-mentioned determination based on the current frame data that there is a vehicle matching any vehicle in the vehicle set among the surrounding vehicles includes: for any vehicle in the vehicle set, if there is a vehicle whose lateral distance with the any vehicle is less than a first preset value and whose longitudinal distance is less than a second preset value among the surrounding vehicles, it is determined that there is a vehicle matching the any vehicle among the surrounding vehicles. For example, if there is a target among the surrounding vehicles whose lateral coordinate minus the lateral coordinate of the predicted target in the vehicle set is less than 1 (calibrable), and the longitudinal position of the target minus the longitudinal position of the predicted target is less than 2 (calibrable), it means that a real sensor target is found near this predicted target.

[0081] The third method is to determine the relative speed between the speed of the last frame of data of each vehicle in the vehicle set before it is lost and the speed of the vehicle itself, and determine the maximum storage time value corresponding to the relative speed. That is, in order to prevent the predicted target in the vehicle set from existing for a long time under certain circumstances, the maximum storage time value can be looked up in a table according to the relative speed between the last frame before the target is lost and the vehicle itself, as shown in Table 1:

[0082] Table 1

[0083]

[0084] Therefore, if the attribute parameter of any vehicle in the vehicle set is greater than the maximum storage time value, the historical data of any vehicle will be cleared.

[0085] It is understandable that if any vehicle in the vehicle set meets any of the above conditions, the validity validFlag of the vehicle is first set to false, and finally by traversing all the vehicle data in the vehicle set, if its validity validFlag is false, the historical data of the vehicle is deleted. In this way, by judging whether the predicted target in the vehicle set has driven out of the target location area, or whether there is a real target near the predicted target, or whether the target is lost for a time greater than the maximum storage time value found according to the relative speed of the target, the predicted target is cleared in time, which can ensure the continuity of the target during the entire process from the rear of the vehicle to the front of the vehicle, and there will be no dangerous lane changing behavior, and the predicted target is cleared in time to ensure that it will not have a negative impact on the NOA function.

[0086] It can be seen that the present application uses the current frame data of the surrounding vehicles detected by the vehicle's sensor to update the historical data of each vehicle stored in a preset memory pool; determines whether there is a target vehicle with lost data in the preset memory pool; if there is a target vehicle with lost data, determines whether the target vehicle is located in a target position area constructed with the vehicle as the center; if it is located in the target position area, predicts the status information of the current frame based on the previous frame data of the target vehicle, and uses the status information as the current frame data of the target vehicle.

[0087] Beneficial effects: A preset memory pool is provided in the present application to store the data of each vehicle. When the vehicle sensor detects the current frame data of the surrounding vehicles, the historical data in the preset memory pool needs to be updated in real time using the current frame data. After completing the update of the memory pool, it is first necessary to determine whether there is a target vehicle that has lost the current frame data in the preset memory pool. If there is a target vehicle that has lost data, it is further determined whether the target vehicle is located in the target position area constructed with the vehicle as the center. If it is located in the target position area, the state information of the current frame is predicted based on the previous frame data of the target vehicle, and the state information is used as the current frame data of the target vehicle. That is, the present application predicts the state of the target vehicle that is suddenly lost in the target position area, and stores the predicted state as its current frame data, instead of immediately releasing the data of the target vehicle, thereby avoiding the sensor suddenly losing the target information due to the blind spot, resulting in dangerous behavior caused by NOA executing the lane change action, and improving the safety of lane change.

[0088] According to the following Figures 3 to 5 The above scheme is described in detail in the following contents:

[0089] First, Figure 3 As shown in the figure, the red rectangle is the key area of ​​concern around the ego vehicle, the black dots in the figure are the target information input by the original sensor, and the target with ID 146 is the right front vehicle target identified by the camera. When the ego vehicle exceeds the right front vehicle, it first enters the camera's blind spot, so the camera target will disappear. Since the target is in the key area of ​​concern for the ego vehicle, it will be predicted, and the following is obtained: Figure 4 At the next moment, the target information of the original sensor is detected near the predicted target again, so the target is cleared in time, as shown in the following figure. Figure 5 As shown, the predicted target with ID 146 was cleared in time.

[0090] That is, the present application adds prediction information for targets in the area of ​​key concern of the ego vehicle to prevent the sudden loss of targets in the sensor's blind spot from causing dangerous NOA lane changes. If there is a vehicle approaching the ego vehicle from behind, the target may be recognized by the radar at the rear. However, when the target vehicle is aligned with the ego vehicle, the vehicle just drives into the radar's blind spot, and neither the front radar nor the rear radar recognizes the target. At this time, the target is briefly predicted. When the target vehicle drives forward for a certain distance, the front radar may recognize the vehicle. At this time, the predicted target is cleared in time, ensuring the continuity of the target vehicle's existence throughout the entire process from the rear of the ego vehicle to the front of the ego vehicle.

[0091] See also Figure 6 As shown, the embodiment of the present application discloses a vehicle data management device, which includes:

[0092] An updating module 11 is used to update the historical data of each vehicle stored in a preset memory pool using the current frame data of each surrounding vehicle detected by the vehicle sensor;

[0093] A first judgment module 12 is used to judge whether there is a target vehicle with lost data in the preset memory pool;

[0094] The second judgment module 13 is used to judge whether the target vehicle is located in the target position area constructed with the vehicle as the center if there is a target vehicle with missing data;

[0095] The prediction module 14 is used to predict the state information of the current frame according to the previous frame data of the target vehicle if the target vehicle is located in the target position area, and use the state information as the current frame data of the target vehicle.

[0096] Beneficial effects: A preset memory pool is provided in the present application to store the data of each vehicle. When the vehicle sensor detects the current frame data of the surrounding vehicles, the historical data in the preset memory pool needs to be updated in real time using the current frame data. After completing the update of the memory pool, it is first necessary to determine whether there is a target vehicle that has lost the current frame data in the preset memory pool. If there is a target vehicle that has lost data, it is further determined whether the target vehicle is located in the target position area constructed with the vehicle as the center. If it is located in the target position area, the state information of the current frame is predicted based on the previous frame data of the target vehicle, and the state information is used as the current frame data of the target vehicle. That is, the present application predicts the state of the target vehicle that is suddenly lost in the target position area, and stores the predicted state as its current frame data, instead of immediately releasing the data of the target vehicle, thereby avoiding the sensor suddenly losing the target information due to the blind spot, resulting in dangerous behavior caused by NOA executing the lane change action, and improving the safety of lane change.

[0097] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle data management method performed by the electronic device disclosed in any of the aforementioned embodiments.

[0098] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0099] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0100] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0101] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the vehicle data management method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data received by the electronic device and transmitted from an external device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0102] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the vehicle data management method steps disclosed in any of the aforementioned embodiments are implemented.

[0103] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0104] Those skilled in the art may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0105] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art.

[0106] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0107] The above is a detailed introduction to a vehicle data management method, device, equipment and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A vehicle data management method, characterized in that: include: The historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor; Determine whether there is a target vehicle with lost data in the preset memory pool; If there is a target vehicle with missing data, determining whether the target vehicle is located in a target location area constructed with the vehicle as the center; If the target vehicle is located in the target position area, the state information of the current frame is predicted according to the previous frame data of the target vehicle, and the state information is used as the current frame data of the target vehicle.

2. The vehicle data management method according to claim 1, characterized in that: Each vehicle in the preset memory pool is provided with an attribute parameter for characterizing the total number of frames of data loss. Before the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor, the method further includes: Determine whether the preset memory pool is empty; If the preset memory pool is not empty, the attribute parameter corresponding to each vehicle in the preset memory pool is incremented by 1, and the historical data in the preset memory pool that meets the preset clearing condition is cleared, and the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor; If the preset memory pool is empty, the historical data of each vehicle stored in the preset memory pool is updated using the current frame data of each surrounding vehicle detected by the vehicle sensor.

3. The vehicle data management method according to claim 2, characterized in that: The method of updating the historical data of each vehicle stored in a preset memory pool by using the current frame data of each surrounding vehicle detected by the vehicle sensor includes: Acquire current frame data of surrounding vehicles detected by the vehicle sensor; wherein the current frame data includes a set of identification numbers and current driving states of the surrounding vehicles; If the first identification number in the identification number set exists in the preset memory pool, the historical driving state corresponding to the first identification number in the preset memory pool is updated using the current driving state corresponding to the first identification number, and the attribute parameter of the vehicle corresponding to the first identification number is assigned to 0; If the second identification number in the identification number set does not exist in the preset memory pool, the second identification number and the corresponding current driving status are added to the preset memory pool, and the attribute parameter of the vehicle corresponding to the second identification number is assigned to 0.

4. The vehicle data management method according to claim 3, characterized in that: The determining whether there is a target vehicle with lost data in the preset memory pool includes: Determine whether there is a vehicle with the attribute parameter greater than 0 in the preset memory pool; If so, the vehicle whose attribute parameter is greater than 0 is determined to be the target vehicle that has lost the current frame data.

5. The vehicle data management method according to claim 2, characterized in that: The clearing of historical data in the preset memory pool that meets the preset clearing condition includes: Traversing the attribute parameters corresponding to each vehicle in the preset memory pool, and determining a set of vehicles whose attribute parameters are greater than 1; The historical data of the vehicles in the vehicle set that meet the preset clearing condition are cleared.

6. The vehicle data management method according to claim 5, characterized in that: The clearing of historical data of vehicles in the vehicle set that meet a preset clearing condition includes: If any vehicle in the vehicle set is not located in the target location area, clearing the historical data of any vehicle; Or, traverse the current frame data of each surrounding vehicle detected by the vehicle sensor, and if it is determined based on the current frame data that there is a vehicle among the surrounding vehicles that matches any vehicle in the vehicle set, clear the historical data of any vehicle; Alternatively, the relative speed between the speed of the last frame of data of each vehicle in the vehicle set before being lost and the speed of the vehicle itself is determined respectively, and a maximum storage time value corresponding to the relative speed is determined; if the attribute parameter of any vehicle in the vehicle set is greater than the maximum storage time value, the historical data of any vehicle is cleared.

7. The vehicle data management method according to claim 6, characterized in that: The determining, based on the current frame data, that there is a vehicle among the surrounding vehicles that matches any vehicle in the vehicle set includes: For any vehicle in the vehicle set, if there is a vehicle among the surrounding vehicles whose lateral distance to the any vehicle is less than a first preset value and whose longitudinal distance to the any vehicle is less than a second preset value, it is determined that there is a vehicle among the surrounding vehicles that matches the any vehicle.

8. A vehicle data management device, characterized in that: include: An updating module, used to update the historical data of each vehicle stored in a preset memory pool using the current frame data of each surrounding vehicle detected by the vehicle sensor; A first judgment module is used to judge whether there is a target vehicle with lost data in the preset memory pool; A second judgment module is used to judge whether the target vehicle is located in a target position area constructed with the vehicle as the center if there is a target vehicle with lost data; The prediction module is used to predict the state information of the current frame according to the previous frame data of the target vehicle if the target vehicle is located in the target position area, and use the state information as the current frame data of the target vehicle.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the vehicle data management method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the steps of the vehicle data management method according to any one of claims 1 to 7 are implemented.

Images