Vehicle tracking method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of vehicles, and discloses a vehicle tracking method and device, computer equipment and a storage medium, and the method comprises the steps: determining other vehicle subsets from other vehicle sets detected by a vehicle when determining a target vehicle as a tracking target of the vehicle according to a tracking target screening condition, the tracking target screening condition corresponding to the own vehicle is preset by a user of the own vehicle; displaying identification information of each other vehicle in the other vehicle subset; and in response to a first target vehicle selected from the other vehicle subset by a user of the own vehicle, controlling the own vehicle to track the first target vehicle.

Description

Technical Field

[0001] This application relates to the technical field of vehicles, and particularly to vehicle tracking methods, devices, computer devices, and storage media. Background Art

[0002] Currently, when a vehicle needs to track other vehicles, for example, during the period when it travels through an adaptive cruise function and needs to track other vehicles, the vehicle to be tracked as the target of the vehicle is determined by the strategy provided by the supplier of the vehicle tracking function to determine the vehicle to be tracked as the target of the vehicle. As a result, the flexibility of the tracking vehicle is poor. How to improve the flexibility of the tracking vehicle has become a problem to be solved. Summary of the Invention

[0003] In view of this, embodiments of the present application provide vehicle tracking methods, devices, computer devices, and storage media.

[0004] In a first aspect, an embodiment of the present application provides a vehicle tracking method, and the method includes:

[0005] When determining a target vehicle that is the tracking target of the host vehicle according to the tracking target screening condition, determining an other vehicle subset from the set of other vehicles detected by the host vehicle, where each other vehicle in the other vehicle subset satisfies the tracking target screening condition corresponding to the host vehicle, and the tracking target screening condition corresponding to the host vehicle is pre-set by the user of the host vehicle;

[0006] Displaying the identification information of each other vehicle in the other vehicle subset;

[0007] In response to the user of the host vehicle selecting a first target vehicle from the other vehicle subset, controlling the host vehicle to track the first target vehicle.

[0008] In a possible implementation, the method further includes:

[0009] In response to detecting that the second target vehicle satisfies the environmental image tracking loss condition during the period of tracking the second target vehicle according to the first environmental image collected by the camera of the host vehicle and the first radar data collected by the radar of the host vehicle, tracking the second target vehicle according to the second radar data collected by the radar, where the second target vehicle is the first target vehicle or a vehicle that is the tracking target of the host vehicle other than the first target vehicle;

[0010] When a candidate vehicle with a second feature matching the first feature of the second target vehicle is detected during the tracking of the second target vehicle based on the second radar data collected by the radar, the candidate vehicle is determined as the second target vehicle, and the second target vehicle is tracked based on the second environmental image collected by the camera and the third radar data collected by the radar, where the first feature is determined based on the first environmental image collected by the camera before it is detected that the second target vehicle satisfies the environmental image tracking loss condition, and the second feature is determined based on the environmental image collected by the camera during the tracking of the second target vehicle based on the second radar data collected by the radar.

[0011] In a possible implementation, the method further includes:

[0012] During the period when the host vehicle is tracking the second target vehicle, the host vehicle receives the driving state information of the second target vehicle, and the driving state information of the second target vehicle includes: the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, the measured position of the second target vehicle, and the measured steering angle of the second target vehicle, where the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is the tracking target of the host vehicle;

[0013] During the period when the host vehicle is tracking the second target vehicle, the host vehicle controls itself based on at least some of the information items in the driving state information of the second target vehicle.

[0014] In a possible implementation, the method further includes:

[0015] During the period when both the host vehicle and the vehicle in front of the host vehicle corresponding to the host vehicle are tracking the second target vehicle, the host vehicle receives the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle, and controls the host vehicle based on at least some of the information items in the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle, where the vehicle in front of the host vehicle corresponding to the host vehicle is the vehicle in front of the host vehicle, and the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle includes: the measured speed of the vehicle in front of the host vehicle corresponding to the host vehicle, the measured acceleration of the vehicle in front of the host vehicle corresponding to the host vehicle, the measured position of the vehicle in front of the host vehicle corresponding to the host vehicle, and the measured steering angle of the vehicle in front of the host vehicle corresponding to the host vehicle.

[0016] In a possible implementation, controlling the host vehicle based on at least some of the information items in the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle includes:

[0017] Controlling the speed of the host vehicle to be the measured speed of the vehicle in front of the host vehicle corresponding to the host vehicle.

[0018] In a possible implementation, the method further includes:

[0019] When multiple vehicles including the host vehicle are traveling in a formation, receive identification information of each vehicle among the multiple vehicles other than the host vehicle from a server for controlling the multiple vehicles to travel in a formation.

[0020] In a second aspect, an embodiment of the present application provides a vehicle tracking device installed on a vehicle. The vehicle tracking device includes:

[0021] A screening unit, configured to determine an other-vehicle subset from the set of other vehicles detected by the host vehicle when a target vehicle that is the tracking target of the host vehicle is determined according to a tracking target screening condition, where each other vehicle in the other-vehicle subset satisfies the tracking target screening condition corresponding to the host vehicle, and the tracking target screening condition corresponding to the host vehicle is preset by the user of the host vehicle;

[0022] A display unit, configured to display the identification information of each other vehicle in the other-vehicle subset;

[0023] A tracking unit, in response to the user of the host vehicle selecting a first target vehicle from the other-vehicle subset, controls the host vehicle to track the first target vehicle.

[0024] In a possible implementation manner, the vehicle tracking device further includes:

[0025] A response unit, configured to, during tracking a second target vehicle based on a first environmental image collected by a camera of the host vehicle and first radar data collected by a radar of the host vehicle, when it is detected that the second target vehicle satisfies an environmental image tracking loss condition, track the second target vehicle according to second radar data collected by the radar, where the second target vehicle is the first target vehicle or a vehicle that is a tracking target of the host vehicle other than the first target vehicle; in response to detecting a candidate vehicle having a second feature matching a first feature of the second target vehicle during tracking the second target vehicle according to the second radar data collected by the radar, determine the candidate vehicle as the second target vehicle, and track the second target vehicle according to a second environmental image collected by the camera and third radar data collected by the radar, where the first feature is determined according to the first environmental image collected by the camera before it is detected that the second target vehicle satisfies the environmental image tracking loss condition, and the second feature is determined according to the environmental image collected by the camera during tracking the second target vehicle according to the second radar data collected by the radar.

[0026] In a possible implementation manner, the vehicle tracking device further includes:

[0027] The first control unit is configured to, during the period when the host vehicle tracks a second target vehicle, the host vehicle receives the driving state information of the second target vehicle, where the driving state information of the second target vehicle includes: the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, the measured position of the second target vehicle, and the measured steering angle of the second target vehicle, and where the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that serves as the tracking target of the host vehicle; during the period when the host vehicle tracks the second target vehicle, the host vehicle controls itself according to at least some of the information items in the driving state information of the second target vehicle.

[0028] In a possible implementation manner, the vehicle tracking device further includes:

[0029] The second control unit is configured to, during the period when the host vehicle and the vehicle in front of the host vehicle both track the second target vehicle, the host vehicle receives the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle, and controls the host vehicle according to at least some of the information items in the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle, where the vehicle in front of the host vehicle corresponding to the host vehicle is the vehicle in front of the host vehicle, and the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle includes: the measured speed of the vehicle in front of the host vehicle corresponding to the host vehicle, the measured acceleration of the vehicle in front of the host vehicle corresponding to the host vehicle, the measured position of the vehicle in front of the host vehicle corresponding to the host vehicle, and the measured steering angle of the vehicle in front of the host vehicle corresponding to the host vehicle.

[0030] In a possible implementation manner, the second control unit is further configured to control the speed of the host vehicle to be the measured speed of the vehicle in front of the host vehicle corresponding to the host vehicle.

[0031] In a possible implementation manner, the vehicle tracking device further includes:

[0032] The receiving unit is configured to, when multiple vehicles including the host vehicle are traveling in a formation, receive the identification information of each vehicle other than the host vehicle in the multiple vehicles from a server for controlling the multiple vehicles to travel in a formation.

[0033] In a third aspect, an embodiment of the present application provides a computer device, including: a memory and a processor, where the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method according to the first aspect or any corresponding implementation manner thereof.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method according to the first aspect or any corresponding implementation manner thereof.

[0035] Fifth aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method according to the first aspect or any corresponding embodiment thereof as described above.

[0036] For the vehicle tracking method provided by the embodiments of the present application, when determining a target vehicle that is the tracking target of the host vehicle according to the tracking target screening conditions, an other vehicle subset is determined from the set of other vehicles detected by the host vehicle; the identification information of each other vehicle in the other vehicle subset is displayed; in response to a user of the host vehicle selecting a first target vehicle from the other vehicle subset, the host vehicle is controlled to track the first target vehicle. The tracking target screening conditions corresponding to the host vehicle are set by a user of the vehicle, such as the owner of the vehicle. Each other vehicle in the other vehicle subset satisfies the tracking target screening conditions corresponding to the host vehicle, and the first target vehicle that satisfies the tracking target screening conditions corresponding to the host vehicle can be regarded as the vehicle that the user of the host vehicle, such as the driver of the host vehicle, expects the host vehicle to track. Therefore, according to the tracking target screening conditions corresponding to the host vehicle, the target vehicle that the user of the host vehicle expects the host vehicle to track can be tracked, improving the flexibility of vehicle tracking and the user experience of the vehicle user. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0038] Figure 1 is a schematic structural diagram of a vehicle that can be used to execute the vehicle tracking method provided by the embodiments of the present application;

[0039] Figure 2 is a schematic flowchart of the vehicle tracking method provided by the embodiments of the present application;

[0040] Figure 3 is a flowchart of an example of selecting a first target vehicle by the vehicle tracking method provided by the embodiments of the present application;

[0041] Figure 4 is a flowchart of another example of selecting a first target vehicle by the vehicle tracking method provided by the embodiments of the present application;

[0042] Figure 5 is a schematic structural diagram of a computer device provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative efforts fall within the scope of protection of this application.

[0044] Reference Figure 1 , which shows a schematic structural diagram of a vehicle that can be used to execute the vehicle tracking method provided in the embodiments of this application.

[0045] The vehicle 101 that can be used to execute the embodiments of this application has a camera 1011, a radar 1012, an interaction and display unit 1013, and a target vehicle tracking unit 1014.

[0046] It should be noted that, in the embodiments of this application, the vehicle serving as the tracking target is called the target vehicle.

[0047] The camera 1011 can collect environmental images of the environment where the vehicle is located. The environmental images include: environmental images of vehicle objects corresponding to other vehicles in front of the vehicle.

[0048] As an example, the radar 1012 is a millimeter-wave radar.

[0049] The radar 1012 can collect radar data of other vehicles on the road where the vehicle 101 is traveling.

[0050] The radar data of other vehicles on the road where the vehicle 101 is traveling includes: the feature data of each point in the point cloud of other vehicles on the road where the vehicle 101 is traveling. The feature data of the point includes: the coordinates of the point, the reflection intensity of the point, and the radial velocity of the point.

[0051] The target vehicle determination unit 1013 can determine the target vehicle that serves as the tracking target of the vehicle 101 when the vehicle 101 needs to track other vehicles on the road where the vehicle 101 is traveling.

[0052] It should be noted that the number of ways to determine the target vehicle that serves as the tracking target of the vehicle 101 can be multiple.

[0053] As an example, multiple ways to determine the target vehicle that serves as the tracking target of the vehicle 101 include: the first way, the second way, the third way, and the fourth way.

[0054] The first way is: to determine the target vehicle that serves as the tracking target of the vehicle 101 according to the tracking target screening conditions corresponding to the vehicle 101.

[0055] The second method is: determining, as the target vehicle for tracking vehicle 101, a target vehicle selected by the user of the host vehicle from among the other vehicles detected by vehicle 101.

[0056] The third method is: determining, as the target vehicle for tracking vehicle 101, a target vehicle according to an instruction sent by the server to vehicle 101 indicating the target vehicle for tracking vehicle 101.

[0057] The fourth method is: determining, as the target vehicle for tracking vehicle 101, a target vehicle according to a strategy provided by the manufacturer of the function of the target tracking vehicle on vehicle 101 for determining the target vehicle for tracking vehicle 101.

[0058] When multiple vehicles including vehicle 101 are traveling in a formation, the server may send an instruction to vehicle 101 indicating the target vehicle for tracking vehicle 101, and the host vehicle determines, according to this instruction, the target vehicle for tracking vehicle 101.

[0059] The driver of vehicle 101 may select the method for determining the target vehicle for tracking vehicle 101.

[0060] The interaction and display unit 1013 may display the identifiers of at least a part of all the methods for determining the target vehicle for tracking vehicle 101. The driver of vehicle 101 may perform a selection operation to select the method for determining the target vehicle for tracking vehicle 101.

[0061] The interaction and display unit 1013 may display the identifier information of the vehicles that may be the target vehicle for tracking vehicle 101.

[0062] As an example, the identifier information of the vehicle may include at least some of the following items: license plate number, brand, model, color.

[0063] The interaction and display unit 1013 may display information related to the target tracking condition item in the target tracking condition, such as candidate condition items that may be the target tracking condition item in the target tracking condition, and an input area for inputting the target tracking condition item in the target tracking condition.

[0064] The target vehicle tracking unit 1014 is used to track the target vehicle for tracking vehicle 101.

[0065] The target vehicle tracking unit 1014 tracking the target vehicle for tracking vehicle 101 may include: detecting other vehicles on the road where vehicle 101 is traveling; determining whether there is a target vehicle for tracking vehicle 101 among the other vehicles detected on the road where vehicle 101 is traveling.

[0066] If the target vehicle tracking unit 1014 determines that there is a target vehicle that is the tracking target of vehicle 101 among the other vehicles detected on the road where vehicle 101 is traveling, then the target vehicle that is the tracking target of vehicle 101 is tracked.

[0067] The target vehicle tracking unit 1014 may include: a target detection network for detecting other vehicles on the road where vehicle 101 is traveling, and a matching unit for determining whether there is a target vehicle that is the tracking target of vehicle 101 among the other vehicles detected on the road where vehicle 101 is traveling.

[0068] The target detection network is: a neural network for detecting targets, such as YOLO, PointNet.

[0069] In addition, the target vehicle tracking unit 1014 may also detect identification information such as the license plate number, brand, model, and color of other vehicles on the road where vehicle 101 is traveling through an image recognition algorithm, such as optical character recognition (OCR).

[0070] Vehicle 101 may communicate with other vehicles on the road where vehicle 101 is traveling through a vehicle-to-everything (V2X) network. When multiple vehicles including vehicle 101 are traveling in a platoon, vehicle 101 may communicate with a server for controlling the multiple vehicles including vehicle 101 to travel in a platoon through the V2X network.

[0071] Reference Figure 2 , which shows a schematic flowchart of the vehicle tracking method provided by an embodiment of the present application. The vehicle tracking method provided by an embodiment of the present application is executed by a host vehicle, and the host vehicle may be any vehicle that can execute the vehicle tracking method provided by an embodiment of the present application.

[0072] In a possible implementation, the vehicle tracking method provided by an embodiment of the present application is executed during the period when the host vehicle is traveling through the adaptive cruise function.

[0073] In step S201, when determining a target vehicle that is the tracking target of the host vehicle according to the tracking target screening condition, an other vehicle subset is determined from the set of other vehicles detected by the host vehicle.

[0074] Wherein, each of the other vehicles in the other vehicle subset meets the tracking target screening condition corresponding to the host vehicle.

[0075] It can also be said that the other vehicle subset is a vehicle set composed of other vehicles in the set of other vehicles detected by the host vehicle that meet the tracking target screening condition corresponding to the host vehicle.

[0076] It should be noted that the target vehicle determined as the tracking target of the host vehicle according to the tracking target screening conditions can be selected by the user of the host vehicle from multiple ways of determining the target vehicle as the tracking target of the host vehicle.

[0077] The tracking target screening conditions corresponding to the host vehicle are preset by the user of the host vehicle, that is, before step S201, the user of the host vehicle sets the tracking target screening conditions corresponding to the host vehicle.

[0078] As an example, the tracking target screening conditions corresponding to the host vehicle may include at least one of the following items: the relative distance between other vehicles and the host vehicle is within the set relative distance range, and the speed of other vehicles is within the set speed range.

[0079] In a possible implementation manner, the set of other vehicles detected by the host vehicle is: the set of all other vehicles detected by the host vehicle.

[0080] In a possible implementation manner, it further includes: when multiple vehicles including the host vehicle are traveling in a formation, receiving the identification information of each vehicle other than the host vehicle in the multiple vehicles from the server for controlling the multiple vehicles to travel in a formation.

[0081] In a possible implementation manner, when multiple vehicles including the host vehicle are traveling in a formation, the set of other vehicles detected by the host vehicle is: the multiple vehicles or a part of the multiple vehicles.

[0082] In step S202, the host vehicle displays the identification information of each other vehicle in the subset of other vehicles.

[0083] As an example, the identification information of other vehicles includes at least some of the following items: the license plate number of other vehicles, the vehicle type of other vehicles, the brand of other vehicles, and the color of other vehicles.

[0084] In step S203, in response to the user of the host vehicle selecting the first target vehicle from the subset of other vehicles, the host vehicle is controlled to track the first target vehicle.

[0085] It should be noted that when the user of the host vehicle selects the first target vehicle from the subset of other vehicles, the user of the host vehicle is in the host vehicle.

[0086] As an example, the user of the host vehicle who selects the first target vehicle from the subset of other vehicles is the driver of the host vehicle.

[0087] As an example, in step S203, the driver of the host vehicle clicks on the control for displaying the identification information of the first target vehicle to select the first target vehicle.

[0088] Reference Figure 3, which shows a flowchart of an example of selecting a first target vehicle through the vehicle tracking method provided by the embodiments of the present application.

[0089] In this example, when the host vehicle is not moving, the user of the host vehicle sets the tracking target screening conditions corresponding to the host vehicle.

[0090] In this example, when the host vehicle is traveling through the adaptive cruise function, the host vehicle detects other vehicles A1, A2,..., AN. Other vehicles A1, A2,..., AN form the set of other vehicles detected by the host vehicle.

[0091] In this example, the host vehicle determines that other vehicles A1 and A2 meet the tracking target screening conditions corresponding to the host vehicle. Other vehicles A1 and A2 form a subset of other vehicles.

[0092] In this example, the host vehicle displays the identification information of other vehicle A1 and the identification information of other vehicle A2.

[0093] In this example, the driver of the host vehicle clicks on the control for displaying the identification information of other vehicle 1 to select other vehicle A1 as the first target vehicle.

[0094] In this example, the host vehicle tracks other vehicle A1.

[0095] Reference Figure 4 , which shows a flowchart of another example of selecting a first target vehicle through the vehicle tracking method provided by the embodiments of the present application.

[0096] In this example, when the host vehicle is not moving, the user of the host vehicle sets the tracking target screening conditions corresponding to the host vehicle.

[0097] In this example, the cloud server instructs the host vehicle, other vehicles B1, B2,..., BN to form a convoy, and the host vehicle, B1, other vehicles B2,..., BN travel in formation.

[0098] In this example, the host vehicle, other vehicles B1, B2,..., BN travel in formation.

[0099] In this example, when the host vehicle is traveling through the adaptive cruise function during the period when the host vehicle, other vehicles B1, B2,..., BN travel in formation, the host vehicle detects other vehicles B1, B2,..., BN. It should be noted that the host vehicle may also detect other vehicles in addition to other vehicles B1, B2,..., BN.

[0100] In this example, other vehicles B1, B2,..., BN form the set of other vehicles detected by the host vehicle.

[0101] In this example, the host vehicle determines that other vehicles B1 and B2 meet the tracking target screening conditions corresponding to the host vehicle. Other vehicles B1 and B2 form a subset of other vehicles.

[0102] In this example, the host vehicle displays the identification information of other vehicle B1 and the identification information of other vehicle B2.

[0103] In this example, the driver of the host vehicle clicks on the control for displaying the identification information of other vehicle B2 to select other vehicle B2 as the first target vehicle.

[0104] In this example, the host vehicle tracks other vehicle B2.

[0105] In a possible implementation of the host vehicle tracking the first target vehicle, the host vehicle can use the environmental images collected by the host vehicle's camera and the radar data collected by the host vehicle's radar to track the first target vehicle. The target detection result corresponding to the t-th environmental image can be obtained based on the t-th environmental image collected by the host vehicle's camera and the radar data corresponding to the t-th environmental image collected by the host vehicle's radar. It can be determined whether there is a first target vehicle among the other vehicles indicated by the target detection result corresponding to the t-th environmental image based on the target detection result corresponding to the t-th environmental image and the target detection result corresponding to the (t - 1)-th environmental image collected by the host vehicle's camera. If it is determined that there is a first target vehicle among the other vehicles indicated by the target detection result corresponding to the t-th environmental image based on the target detection result corresponding to the t-th environmental image and the target detection result corresponding to the (t - 1)-th environmental image, then the first target vehicle is tracked.

[0106] Among them, the t-th environmental image can be: the environmental images collected during the host vehicle tracking the first target vehicle except for the first collected environmental image.

[0107] The radar data corresponding to the t-th environmental image can be: the radar data with the closest acquisition time to the acquisition time of the t-th environmental image.

[0108] The target detection result corresponding to the t-th environmental image can indicate: the predicted speed of the detected other vehicle, the predicted acceleration of the detected other vehicle, the predicted position of the detected other vehicle, the predicted steering angle of the detected other vehicle, and the relative distance between the detected other vehicle and the host vehicle.

[0109] It should be noted that the detected other vehicles can be represented by the vehicle identification of the detected other vehicles.

[0110] In a possible implementation of obtaining the object detection result corresponding to the t-th environmental image, the object detection result corresponding to the t-th environmental image can be obtained through feature fusion. The features obtained by performing feature extraction on the t-th environmental image and the features obtained by performing feature extraction on the radar data corresponding to the t-th environmental image can be fused to obtain the fused features corresponding to the t-th environmental image. The fused features corresponding to the t-th environmental image are input into an object detection network that performs object detection based on the fused features to obtain the object detection result corresponding to the t-th environmental image.

[0111] In addition, when obtaining the object detection result corresponding to the t-th environmental image through feature fusion, if it is necessary to determine whether the first target vehicle appears in the environmental image, the features obtained by performing feature extraction on the t-th environmental image can be input into a neural network that performs object detection based on the environmental image to obtain the object detection result for the t-th environmental image. If it is determined that the first target vehicle is among the other vehicles indicated by the object detection result for the t-th environmental image according to the object detection result for the t-th environmental image and the object detection result for the (t - 1)-th environmental image, it can be determined that the first target vehicle appears in the t-th environmental image.

[0112] In another possible implementation of obtaining the object detection result corresponding to the t-th environmental image, the object detection result corresponding to the t-th environmental image can be obtained through result fusion. The features obtained by performing feature extraction on the t-th environmental image are input into a neural network that performs object detection based on the environmental image to obtain the object detection result for the t-th environmental image. The features obtained by performing feature extraction on the radar data corresponding to the t-th environmental image are input into a neural network that performs object detection based on the radar data to obtain the object detection result for the radar data corresponding to the t-th environmental image. The object detection result for the t-th environmental image and the object detection result for the radar data corresponding to the t-th environmental image are fused to obtain the object detection result corresponding to the t-th environmental image.

[0113] In a possible implementation, the relative distance between the host vehicle and the first target vehicle in the object detection result corresponding to the t-th environmental image can be used as the relative distance between the first target vehicle and the host vehicle corresponding to the t-th environmental image. The predicted speed of the first target vehicle in the object detection result corresponding to the t-th environmental image can be used as the target speed of the first target vehicle corresponding to the t-th environmental image. The Kalman filtering algorithm can also be used to determine the target speed of the first target vehicle corresponding to the t-th environmental image based on the predicted speed of the first target vehicle in the object detection result corresponding to the t-th environmental image and the target speed of the first target vehicle corresponding to the (t - 1)-th environmental image. The predicted position of the first target vehicle in the object detection result corresponding to the t-th environmental image can be used as the target position of the first target vehicle corresponding to the t-th environmental image. The Kalman filtering algorithm can also be used to determine the target position of the first target vehicle corresponding to the t-th environmental image based on the predicted position of the first target vehicle in the object detection result corresponding to the t-th environmental image and the target position of the first target vehicle corresponding to the (t - 1)-th environmental image. The predicted acceleration of the first target vehicle in the object detection result corresponding to the t-th environmental image can be used as the target acceleration of the first target vehicle corresponding to the t-th environmental image. The target acceleration of the first target vehicle corresponding to the t-th environmental image can also be determined based on the predicted acceleration of the first target vehicle in the object detection result corresponding to the t-th environmental image and the target acceleration of the first target vehicle corresponding to the (t - 1)-th environmental image. The predicted steering angle of the first target vehicle in the object detection result corresponding to the t-th environmental image can be used as the target steering angle of the first target vehicle corresponding to the t-th environmental image. The target steering angle of the first target vehicle corresponding to the t-th environmental image can also be determined based on the predicted steering angle of the first target vehicle in the object detection result corresponding to the t-th environmental image and the target steering angle of the first target vehicle corresponding to the (t - 1)-th environmental image.

[0114] In a possible implementation of the host vehicle tracking the first target vehicle, only the radar data collected by the host vehicle's radar can be used to track the first target vehicle. Other vehicles on the road where the host vehicle is traveling can be detected based on the t-th radar data collected by the host vehicle's radar. The t-th radar data is input into an object detection network for object detection based on radar data to obtain the object detection result corresponding to the t-th radar data. Whether there is a first target vehicle among the other vehicles indicated by the object detection result corresponding to the t-th radar data can be determined based on the object detection result corresponding to the t-th radar data and the object detection result corresponding to the (t - 1)-th radar data collected by the host vehicle's radar. If it is determined that there is a first target vehicle among the other vehicles indicated by the object detection result corresponding to the t-th radar data, then the first target vehicle is tracked.

[0115] The t-th radar data may be: the radar data collected by the host vehicle during the period of tracking the first target vehicle, excluding the first radar data collected.

[0116] In an embodiment of the present application, a target detection network for target detection based on radar data may extract features from the t-th radar data to obtain the features corresponding to the t-th radar data, and predict the target detection result corresponding to the t-th radar data according to the features corresponding to the t-th radar data. In addition, when tracking the first target vehicle only using the radar data collected by the host vehicle's radar, if it is necessary to determine whether the first target vehicle appears in the environmental image, the features obtained by extracting the features of the environmental image corresponding to the t-th radar data may be input into a neural network for target detection based on the features of the environmental image, so that the neural network for target detection based on the features of the environmental image extracts the features of the environmental image corresponding to the t-th radar data.

[0117] The t-th radar data is: the radar data collected by the host vehicle during the period of tracking the first target vehicle, excluding the first radar data collected.

[0118] The environmental image corresponding to the t-th radar data may be: the radar data with the closest acquisition time to the acquisition time of the t-th environmental image.

[0119] The target detection result corresponding to the t-th radar data indicates: the predicted speed of the detected other vehicle, the predicted acceleration of the detected other vehicle, the predicted position of the detected other vehicle, the predicted steering angle of the detected other vehicle, and the relative distance between the detected other vehicle and the host vehicle.

[0120] In a possible implementation, the relative distance between the host vehicle and the first target vehicle in the target detection result corresponding to the t-th radar data can be used as the relative distance between the first target vehicle and the host vehicle corresponding to the t-th radar data. The predicted speed of the first target vehicle in the target detection result corresponding to the t-th radar data can be used as the target speed of the first target vehicle corresponding to the t-th radar data. The Kalman filtering algorithm can also be used to determine the target speed of the first target vehicle corresponding to the t-th radar data based on the predicted speed of the first target vehicle in the target detection result corresponding to the t-th radar data and the target speed of the first target vehicle corresponding to the (t - 1)-th radar data. The predicted acceleration of the first target vehicle in the target detection result corresponding to the t-th radar data can be used as the target acceleration of the first target vehicle corresponding to the t-th radar data. The Kalman filtering algorithm can also be used to determine the target acceleration of the first target vehicle corresponding to the t-th radar data based on the predicted acceleration of the first target vehicle in the target detection result corresponding to the t-th radar data and the target acceleration of the first target vehicle corresponding to the (t - 1)-th radar data. The predicted position of the first target vehicle in the target detection result corresponding to the t-th radar data can be used as the target position of the first target vehicle corresponding to the t-th radar data. The Kalman filtering algorithm can also be used to determine the target position of the first target vehicle corresponding to the t-th radar data based on the predicted position of the first target vehicle in the target detection result corresponding to the t-th radar data and the target position of the first target vehicle corresponding to the (t - 1)-th radar data. The predicted steering angle of the first target vehicle in the target detection result corresponding to the t-th radar data can be used as the target steering angle of the first target vehicle corresponding to the t-th radar data. The Kalman filtering algorithm can also be used to determine the target steering angle of the first target vehicle corresponding to the t-th radar data based on the predicted steering angle of the first target vehicle in the target detection result corresponding to the t-th radar data and the target steering angle of the first target vehicle corresponding to the (t - 1)-th radar data.

[0121] In the embodiments of the present application, during the period when the host vehicle tracks the first target vehicle, the host vehicle can control itself based on at least a part of the relative distance between the first target vehicle and the host vehicle, the target speed of the first target vehicle, the target acceleration of the first target vehicle, the target position of the first target vehicle, and the target steering angle of the first target vehicle.

[0122] In a possible implementation, during the period of tracking the first target vehicle, the host vehicle controls the relative distance between itself and the first target vehicle to be a safe following distance based on the relative distance between the first target vehicle and the host vehicle, the target speed of the first target vehicle, and the target position of the first target vehicle.

[0123] In a possible implementation, during the period when the host vehicle tracks the first target vehicle, the host vehicle controls the acceleration of the host vehicle based on the relative distance between the host vehicle and the first target vehicle, the acceleration of the first target vehicle, and the difference between the speed of the host vehicle and the target speed of the first target vehicle, so as to control the relative distance between the host vehicle and the first target vehicle to be always or almost always within the safe following distance.

[0124] In a possible implementation, the speed of the first target vehicle is V1, and the difference between the speed of the host vehicle and the speed of the target vehicle is preset as ΔV. During the period when the host vehicle tracks the first target vehicle, the host vehicle controls the speed of the host vehicle to be V1 + ΔV, so as to control the relative distance between the host vehicle and the first target vehicle not only to be within the safe following distance, but also to make the relative distance between the host vehicle and the first target vehicle stable.

[0125] In a possible implementation, during the period when the host vehicle tracks the first target vehicle, when the host vehicle is driving on a curve, the steering angle of the host vehicle is controlled according to the driving trajectory of the first target vehicle, the target steering angle of the first target vehicle, the position of the host vehicle, and the speed of the host vehicle, so that when the host vehicle tracks the first target vehicle, the host vehicle can smoothly pass through the curve, and the safety of the host vehicle when driving on the curve is improved.

[0126] In a possible implementation, it further includes: step S204.

[0127] In step S204, in response to detecting that the second target vehicle satisfies the environmental image tracking loss condition during the period of tracking the second target vehicle according to the first environmental image collected by the camera of the host vehicle and the first radar data collected by the radar of the host vehicle, the second target vehicle is tracked according to the second radar data collected by the radar of the host vehicle, where the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is the tracking target of the host vehicle; in response to detecting a candidate vehicle with a second feature that matches the first feature of the second target vehicle during the period of tracking the second target vehicle according to the second radar data collected by the radar of the host vehicle, the candidate vehicle is determined as the second target vehicle, and the second target vehicle is tracked according to the second environmental image collected by the camera of the host vehicle and the third radar data collected by the radar of the host vehicle, where the first feature is determined according to the first environmental image collected by the camera of the host vehicle before detecting that the second target vehicle satisfies the environmental image tracking loss condition, and the second feature is determined according to the environmental image collected by the camera of the host vehicle during the period of tracking the second target vehicle according to the second radar data collected by the radar.

[0128] It should be noted that the second target vehicle satisfying the environmental image tracking loss condition can reflect that the second target vehicle does not appear in the corresponding environmental image collected by the camera of the host vehicle.

[0129] Generally, the second target vehicle meets the environmental image tracking loss condition because the second target vehicle is blocked by other vehicles.

[0130] In a possible implementation, the environmental image tracking loss condition is that the second target vehicle does not appear in the first environmental image m. Here, the first environmental image m is the first environmental image collected by the vehicle's camera during the period of tracking the second target vehicle based on the first environmental image collected by the vehicle's camera and the first radar data collected by the vehicle's radar.

[0131] Among them, in order to determine whether the second target vehicle appears in the first environmental image m, the features obtained by feature extraction of the first environmental image m can be input into a neural network for target detection based on the environmental image to obtain the target detection result for the first environmental image m. If it is determined that there is a second target vehicle among the other vehicles indicated by the target detection result for the first environmental image m according to the target detection result for the first environmental image m and the target detection result for the first environmental image m-1, it can be determined that the second target vehicle appears in the t-th environmental image. Here, the first environmental image m-1 is the previous first environmental image of the first environmental image m. If it is determined that there is no target vehicle among the other vehicles indicated by the target detection result for the first environmental image m according to the target detection result for the first environmental image m and the target detection result for the first environmental image m-1, it can be determined that the second target vehicle does not appear in the first environmental image m, and it can be determined that the environmental image tracking loss condition is met.

[0132] In another possible implementation, the environmental image tracking loss condition is that for each of a continuous plurality of first environmental images, the second target vehicle does not appear in the first environmental image. The continuous plurality of first environmental images are the plurality of first environmental images collected by the vehicle's camera during the period of tracking the second target vehicle based on the first environmental image collected by the vehicle's camera and the first radar data collected by the vehicle's radar.

[0133] It should be noted that the second radar data is collected after detecting that the second target vehicle meets the environmental image tracking loss condition.

[0134] During the period of tracking the second target vehicle based on the second radar data collected by this radar, other vehicles on the road where the vehicle is traveling are detected according to the second radar data collected by the vehicle's radar. During the period of tracking the second target vehicle based on the second radar data collected by this radar, for each second radar data collected by the vehicle's radar each time, the second radar data can be input into a target detection network for target detection based on radar data to obtain the target detection result corresponding to the second radar data.

[0135] It should be noted that the first feature of the second target vehicle is obtained by a neural network for feature extraction of environmental images extracting features from the first environmental image corresponding to the first feature. The second target vehicle appears in the environmental image corresponding to the first feature.

[0136] In a possible implementation, the first environmental image corresponding to the first feature may be: the first environmental image with the latest acquisition time among the first environmental images acquired by the camera of the host vehicle before the acquisition time of the first environmental image j. Among them, determining that the environmental image tracking loss condition is met is determined according to the first environmental image j and the previous first environmental image of the first environmental image j, that is, the first environmental image j-1. According to the target detection result for the first environmental image j and the target detection result for the first environmental image j-1, if it is determined that there is no target vehicle among the other vehicles indicated by the target detection result for the first environmental image j, it can be determined that the second target vehicle does not appear in the first environmental image j, and it can be determined that the environmental image tracking loss condition is met.

[0137] It should be noted that the second feature is obtained by extracting features from the third environmental image corresponding to the second feature.

[0138] The third environmental image is an environmental image acquired during the period of tracking the second target vehicle based on the second radar data collected by the radar of the host vehicle.

[0139] Before detecting a candidate vehicle with a second feature that matches the first feature of the second target vehicle, each time a third environmental image is acquired, the third environmental image can be subjected to feature extraction to obtain the second feature of the third environmental image, and the second feature of the third environmental image is matched with the first feature.

[0140] It should be noted that the second environmental image is acquired by the camera of the host vehicle after determining the candidate vehicle as the second target vehicle. The third radar data is collected by the radar of the host vehicle after determining the candidate vehicle as the second target vehicle.

[0141] In an embodiment of the present application, step S204 takes into account that the second target vehicle meeting the environmental image tracking loss condition can reflect that the second target vehicle does not appear in the corresponding environmental image. The environmental image collected when the second target vehicle meets the environmental image tracking loss condition cannot obtain data that can be used to track the second target vehicle. Therefore, only radar data is used to track the second target vehicle, and the environmental image that cannot obtain data for tracking the second target vehicle is not utilized, saving the resources consumed in tracking the second target vehicle. After determining the candidate vehicle with the second feature matching the first feature of the second target vehicle as the second target vehicle, the environmental image and radar data can be used again to track the second target vehicle. Since, compared with only using radar data to track the second target vehicle, the data used for tracking is richer when using the environmental image and radar data to track the second target vehicle, the parameters such as the position and speed of the determined second target vehicle are more accurate, and a better tracking effect can be achieved. At the same time, determining the candidate vehicle with the second feature matching the first feature of the second target vehicle as the second target vehicle can avoid the following situation: when the second target vehicle appears in the environmental image collected after the second target vehicle meets the environmental image tracking loss condition, the second target vehicle is recognized as a newly appeared vehicle, resulting in the failure of tracking the second target vehicle.

[0142] In a possible implementation manner, it further includes: step S205.

[0143] In step S205, during the period when the host vehicle tracks the second target vehicle, the host vehicle receives the driving state information of the second target vehicle. The driving state information of the second target vehicle includes: the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, the measured position of the second target vehicle, and the measured steering angle of the second target vehicle. Herein, the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is the tracking target of the host vehicle; during the period when the host vehicle tracks the second target vehicle, the host vehicle controls the host vehicle according to at least some information items in the driving state information of the second target vehicle.

[0144] It should be noted that the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, the measured position of the second target vehicle, and the measured steering angle of the second target vehicle are all obtained by the second target vehicle through corresponding measurements.

[0145] In a possible implementation manner, during the period when the host vehicle tracks the second target vehicle, the host vehicle can receive the driving state information of the second target vehicle from the second target vehicle through the vehicle network.

[0146] In a possible implementation, the period during which the host vehicle tracks the second target vehicle is a sub-period during which multiple vehicles including the host vehicle are driving in a formation. The host vehicle may receive the driving state information of the second target vehicle from a server for controlling the multiple vehicles to drive in a formation. The driving state information of the second target vehicle is sent by the second target vehicle to the server.

[0147] In step S205, the host vehicle may use the position measured by the second target vehicle as the target position of the second target vehicle. The host vehicle may use the measured speed of the second target vehicle as the target speed of the second target vehicle. The host vehicle may use the measured acceleration of the second target vehicle as the target acceleration of the second target vehicle. The host vehicle may use the measured steering angle of the second target vehicle as the target steering angle of the second target vehicle. The host vehicle may control the host vehicle based on at least a part of the position measured by the second target vehicle, the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, and the target steering angle of the second target vehicle.

[0148] Step S205 takes into account that: the position measured by the second target vehicle, the measured acceleration of the second target vehicle, the measured speed of the second target vehicle, and the measured steering angle of the second target vehicle are all measured by the second target vehicle, and the accuracy of the position measured by the second target vehicle, the accuracy of the measured acceleration of the second target vehicle, the accuracy of the measured speed of the second target vehicle, and the accuracy of the measured steering angle of the second target vehicle are all relatively high. During the period when the host vehicle tracks the second target vehicle, the host vehicle controls the host vehicle based on at least a part of the position measured by the second target vehicle, the measured acceleration of the second target vehicle, the measured speed of the second target vehicle, and the measured steering angle of the second target vehicle, which can control the host vehicle more precisely. It is possible to more precisely control at least one of the speed of the host vehicle, the acceleration of the host vehicle, and the steering angle of the host vehicle. It is possible to more precisely control the relative distance between the host vehicle and the second target vehicle to be a safe following distance. The safety of the host vehicle tracking the second target vehicle is improved.

[0149] In a possible implementation, it further includes: step S206.

[0150] In step S206, it further includes: during the period when both the host vehicle and the vehicle in front of the host vehicle corresponding to the host vehicle track the second target vehicle, the host vehicle receives the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle, and controls the host vehicle according to at least some information items in the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle. The vehicle in front of the host vehicle corresponding to the host vehicle is the vehicle in front of the host vehicle. The driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle includes: the measured speed of the vehicle in front of the host vehicle corresponding to the host vehicle, the measured acceleration of the vehicle in front of the host vehicle corresponding to the host vehicle, the measured position of the vehicle in front of the host vehicle corresponding to the host vehicle, and the measured steering angle of the vehicle in front of the host vehicle corresponding to the host vehicle.

[0151] It should be noted that the measured speed of the vehicle in front of the host vehicle, the measured acceleration of the vehicle in front of the host vehicle, the measured position of the vehicle in front of the host vehicle, and the steering angle of the vehicle in front of the host vehicle are all measured by the second target vehicle.

[0152] In a possible implementation, during the period when both the host vehicle and the vehicle in front of the host vehicle are tracking the second target vehicle, the host vehicle can receive the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle through the vehicle network.

[0153] In a possible implementation, the period when both the host vehicle and the vehicle in front of the host vehicle are tracking the second target vehicle is a sub-period during which multiple vehicles including the host vehicle are driving in formation. The host vehicle and the vehicle in front of the host vehicle are both vehicles among the multiple vehicles, and the host vehicle and the vehicle in front of the host vehicle belong to the same fleet. The host vehicle can receive the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle from the server used to control the multiple vehicles to drive in formation. Among them, the driving state information of the vehicle in front of the host vehicle corresponding to the host vehicle is sent by the vehicle in front of the host vehicle corresponding to the host vehicle to the server.

[0154] In a possible implementation, in step S206, controlling the host vehicle according to at least some information items in the driving state information of the vehicle in front of the host vehicle includes: planning a driving trajectory that can avoid the host vehicle from colliding with the vehicle in front of the host vehicle when both the host vehicle and the vehicle in front of the host vehicle are tracking the second target vehicle; controlling the host vehicle to drive along the driving trajectory.

[0155] Through step S206, the host vehicle can more accurately plan a driving trajectory that can avoid the host vehicle from colliding with the vehicle in front of the host vehicle when both the host vehicle and the vehicle in front of the host vehicle are tracking the second target vehicle, improving the safety of the tracking vehicle when both the host vehicle and the vehicle in front of the host vehicle are tracking the second target vehicle.

[0156] In a possible implementation, step S206 includes: step S2061.

[0157] In step S2061, controlling the host vehicle according to at least some information items in the driving state information of the vehicle in front of the host vehicle includes: the host vehicle controlling the speed of the host vehicle to be the measured speed of the vehicle in front of the host vehicle.

[0158] In step S2061, the host vehicle can determine the measured speed of the vehicle in front of the host vehicle as the target speed of the vehicle in front of the host vehicle. The host vehicle controls the speed of the host vehicle to be the measured speed of the vehicle in front of the host vehicle.

[0159] Step S2061 considers that when the host vehicle and the vehicle ahead corresponding to the host vehicle track the same target vehicle, i.e., the second target vehicle, the host vehicle can control its speed to be the speed measured with higher accuracy of the vehicle ahead corresponding to the host vehicle. Thus, the speed of the host vehicle is the same as the speed measured with higher accuracy of the vehicle ahead corresponding to the host vehicle. This makes the relative distance between the host vehicle and the vehicle ahead corresponding to the host vehicle stable when they track the same target vehicle, avoiding the situation where the relative distance between the host vehicle and the vehicle ahead corresponding to the host vehicle is far and near, and at the same time, avoiding the situation of collision when the host vehicle and the vehicle ahead corresponding to the host vehicle track the same vehicle. This improves the safety of the tracking vehicle when the host vehicle and the vehicle ahead corresponding to the host vehicle track the same target vehicle.

[0160] The embodiments of the present application provide a vehicle tracking device. The vehicle tracking device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "unit" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0161] The vehicle tracking device is installed on a vehicle, and the vehicle tracking device includes:

[0162] A screening unit, configured to determine an other vehicle subset from the set of other vehicles detected by the host vehicle when determining a target vehicle that is the tracking target of the host vehicle according to the tracking target screening condition, where each other vehicle in the other vehicle subset meets the tracking target screening condition corresponding to the host vehicle, and the tracking target screening condition corresponding to the host vehicle is preset by the user of the host vehicle;

[0163] A display unit, configured to display the identification information of each other vehicle in the other vehicle subset;

[0164] A tracking unit, in response to the user of the host vehicle selecting a first target vehicle from the other vehicle subset, controls the host vehicle to track the first target vehicle.

[0165] In a possible implementation manner, the vehicle tracking device further includes:

[0166] A response unit, configured to, during the process of tracking a second target vehicle based on a first environmental image collected by a camera of the host vehicle and first radar data collected by a radar of the host vehicle, when it is detected that the second target vehicle meets the environmental image tracking loss condition, track the second target vehicle according to second radar data collected by the radar, where the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is a tracking target of the host vehicle; when a candidate vehicle with a second feature matching the first feature of the second target vehicle is detected during the process of tracking the second target vehicle according to the second radar data collected by the radar, determine the candidate vehicle as the second target vehicle, and track the second target vehicle according to a second environmental image collected by the camera and third radar data collected by the radar, where the first feature is determined according to the first environmental image collected by the camera before it is detected that the second target vehicle meets the environmental image tracking loss condition, and the second feature is determined according to the environmental image collected by the camera during the process of tracking the second target vehicle according to the second radar data collected by the radar.

[0167] In a possible implementation, the vehicle tracking device further includes:

[0168] A first control unit, configured to, during the process of the host vehicle tracking the second target vehicle, the host vehicle receives driving state information of the second target vehicle, where the driving state information of the second target vehicle includes: the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, the measured position of the second target vehicle, the measured steering angle of the second target vehicle, where the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is a tracking target of the host vehicle; during the process of the host vehicle tracking the second target vehicle, the host vehicle controls itself according to at least some of the information items in the driving state information of the second target vehicle.

[0169] In a possible implementation, the vehicle tracking device further includes:

[0170] A second control unit, configured to, during the process of both the host vehicle and a vehicle in front of the host vehicle tracking the second target vehicle, the host vehicle receives the driving state information of the vehicle in front of the host vehicle, and controls the host vehicle according to at least some of the information items in the driving state information of the vehicle in front of the host vehicle, where the vehicle in front of the host vehicle is a vehicle in front of the host vehicle, and the driving state information of the vehicle in front of the host vehicle includes: the measured speed of the vehicle in front of the host vehicle, the measured acceleration of the vehicle in front of the host vehicle, the measured position of the vehicle in front of the host vehicle, the measured steering angle of the vehicle in front of the host vehicle.

[0171] In a possible implementation, the second control unit is further configured to control the speed of the host vehicle to be the measured speed corresponding to the vehicle in front of the host vehicle.

[0172] In a possible implementation, the vehicle tracking device further includes:

[0173] a receiving unit, configured to, when multiple vehicles including the host vehicle are traveling in a formation, receive the identification information of each vehicle other than the host vehicle among the multiple vehicles from a server for controlling the multiple vehicles to travel in a formation.

[0174] In this embodiment, the device is presented in the form of functional units. Here, the unit refers to an ASIC circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0175] The further function descriptions of the above units are the same as those in the corresponding embodiments above, and will not be elaborated here.

[0176] Reference Figure 5 , which shows a schematic structural diagram of a computer device provided in an embodiment of the present application. The computer device is installed on a vehicle. The computer device includes: one or more processors 10, a memory 20, and an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component communicates with each other through different buses and can be installed on a common main board or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system).

[0177] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0178] Wherein, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0179] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0180] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may also include a combination of the above types of memories.

[0181] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means.

[0182] The input device 30 may receive input digital or character information, and generate key signal inputs related to the user settings and function controls of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light-emitting diode, a display, and a plasma display. In some alternative embodiments, the display device may be a touch screen.

[0183] The embodiments of the present application also provide a computer-readable storage medium. The methods according to the embodiments of the present application can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the methods described herein can be processed by such software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0184] A part of the embodiments of the present application can be applied as a computer program product, for example, computer program instructions. When executed by a computer, through the operation of the computer, the methods and / or technical solutions according to the present invention can be invoked or provided. Those skilled in the art should understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.

[0185] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A vehicle tracking method, characterized in that: The method comprises: When determining a target vehicle as a tracking target of the own vehicle according to the tracking target screening condition, determining a subset of other vehicles from a set of other vehicles detected by the own vehicle, wherein each other vehicle in the subset of other vehicles satisfies the tracking target screening condition corresponding to the own vehicle, and the tracking target screening condition corresponding to the own vehicle is pre-set by a user of the own vehicle; displaying identification information of each other vehicle in the subset of other vehicles; In response to a user of the own vehicle selecting a first target vehicle from the subset of other vehicles, the own vehicle is controlled to track the first target vehicle.

2. The method according to claim 1, characterized in that The method further comprises: In response to detecting that the second target vehicle meets an environment image tracking loss condition during tracking of the second target vehicle based on the first environment image collected by the camera of the own vehicle and the first radar data collected by the radar of the own vehicle, tracking the second target vehicle based on the second radar data collected by the radar, wherein the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is a tracking target of the own vehicle; In response to detecting a candidate vehicle having a second feature that matches the first feature of the second target vehicle during tracking of the second target vehicle based on second radar data collected by the radar, the candidate vehicle is determined as the second target vehicle, and the second target vehicle is tracked based on the second environmental image collected by the camera and the third radar data collected by the radar, wherein the first feature is determined based on the first environmental image collected by the camera before the second target vehicle is detected to meet the environmental image tracking loss condition, and the second feature is determined based on the environmental image collected by the camera during tracking of the second target vehicle based on the second radar data collected by the radar.

3. The method according to claim 1, characterized in that: The method further comprises: During the period when the ego vehicle tracks the second target vehicle, the ego vehicle receives the driving state information of the second target vehicle, and the driving state information of the second target vehicle includes: the measured speed of the second target vehicle, the measured acceleration of the second target vehicle, the measured position of the second target vehicle, and the measured steering angle of the second target vehicle, wherein the second target vehicle is the first target vehicle or a vehicle other than the first target vehicle that is a tracking target of the ego vehicle; During the period when the ego vehicle tracks the second target vehicle, the ego vehicle controls the ego vehicle according to at least part of the information items in the driving state information of the second target vehicle.

4. The method according to claim 1, characterized in that: The method further comprises: During the period when both the self-vehicle and the vehicle in front of the self-vehicle are tracking the second target vehicle, the self-vehicle receives the driving status information of the vehicle in front of the self-vehicle, and controls the self-vehicle according to at least part of the information items in the driving status information of the vehicle in front of the self-vehicle, wherein the vehicle in front of the self-vehicle is the vehicle in front of the self-vehicle, and the driving status information of the vehicle in front of the self-vehicle includes: the measured speed of the vehicle in front of the self-vehicle, the measured acceleration of the vehicle in front of the self-vehicle, the measured position of the vehicle in front of the self-vehicle, and the measured steering angle of the vehicle in front of the self-vehicle.

5. The method according to claim 4, characterized in that According to at least part of the information items in the driving state information of the vehicle ahead of the own vehicle, controlling the own vehicle comprises: The speed of the own vehicle is controlled to correspond to the measured speed of the vehicle ahead of the own vehicle.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: When a plurality of vehicles including an own vehicle travel in a platoon, identification information of each of the plurality of vehicles other than the own vehicle is received from a server for controlling the plurality of vehicles to travel in a platoon.

7. A vehicle tracking device, characterized in that: Installed on a vehicle, the device comprises: a screening unit, configured to, when determining a target vehicle as a tracking target of the own vehicle according to the tracking target screening condition, determine a subset of other vehicles from a set of other vehicles detected by the own vehicle, wherein each other vehicle in the subset of other vehicles satisfies the tracking target screening condition corresponding to the own vehicle, and the tracking target screening condition corresponding to the own vehicle is pre-set by a user of the own vehicle; a display unit, configured to display identification information of each other vehicle in the subset of other vehicles; The tracking unit controls the vehicle to track the first target vehicle in response to a user of the vehicle selecting the first target vehicle from the subset of other vehicles.

8. A computer device, characterized in that: Installed on the vehicle, including: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method according to any one of claims 1 to 6.

Images