An object recognition processing method, device, equipment and storage medium

Abstract

Embodiments of the present application disclose a target object identification processing method, device and equipment, and a storage medium. The method comprises: acquiring a field of view image of a transverse region in front of a vehicle; determining a region of interest of the field of view image according to a field of view angle of the vehicle, and identifying a target object in the region of interest; determining movement data of the target object according to position information of the vehicle and the target object, and outputting the movement data. The method can identify objects in the region of interest in front of the vehicle, can reduce the region of identification processing, and thus can reduce the amount of calculation and save resources.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of vehicle driving, and particularly relate to a target object identification processing method and device, equipment and a storage medium. BACKGROUND

[0002] With the improvement of people's living standards, more and more vehicles are on the road, and the driving safety of vehicles is also more and more concerned. When driving, vehicles often encounter the phenomenon of objects crossing, which brings safety hazards to vehicle driving.

[0003] In the prior art, objects in the entire field of view range in front of the vehicle are uniformly identified to ensure the safety of vehicle driving. However, with the increase of the types and quantities of objects on the road, the number of objects that need to be identified increases, the calculation amount is large, and the calculation cost is high. Especially when considering the object crossing phenomenon, the number of objects that need to be identified will be more. SUMMARY

[0004] Embodiments of the present application provide a target object identification processing method, device, equipment and storage medium, which can identify objects in the interested area in front of the vehicle, reduce the identification processing area, and thus reduce the calculation amount and save resources.

[0005] In a first aspect, embodiments of the present application provide a target object identification processing method, which comprises:

[0006] Obtaining a field of view image of a lateral area in front of a vehicle;

[0007] According to the field of view angle of the vehicle, determining an interested area of the field of view image, and identifying a target object in the interested area;

[0008] According to the position information of the vehicle and the target object, determining movement data of the target object, and outputting the movement data.

[0009] Optionally, according to the field of view angle of the vehicle, determining the interested area of the field of view image, and identifying the target object in the interested area, comprises:

[0010] According to the field of view angle of the vehicle, the region in which the object moves laterally in the field of view image is taken as a first interested area, and the region in which the object moves longitudinally is taken as a second interested area;

[0011] A first target object is identified in the first interested area, and a second target object is identified in the second interested area.

[0012] Optionally, according to the field of view angle of the vehicle, the region in which the object in the field of view image moves laterally is taken as a first region of interest, and the region in which the object moves longitudinally is taken as a second region of interest, comprising:

[0013] The lateral region in the field of view image when the field of view angle of the vehicle camera is less than or equal to 52 degrees is taken as the second region of interest.

[0014] The remaining region in the field of view image after the second region of interest is removed is taken as the first region of interest.

[0015] Optionally, the first target object includes a pedestrian, a two-wheeled vehicle, a three-wheeled vehicle, and a pet.

[0016] The second target object includes a pedestrian, a two-wheeled vehicle, a three-wheeled vehicle, a pet, and a vehicle with three or more wheels.

[0017] Optionally, according to the position information of the vehicle and the target object, the movement data of the target object is determined, and the movement data is output, comprising:

[0018] According to the position information of the vehicle and the target object, the movement data of the first target object in the first region of interest is determined.

[0019] According to the position information of the vehicle and the target object, the movement data of the second target object in the second region of interest is determined.

[0020] Optionally, the movement data includes at least one of the following: object type, longitudinal distance of the target object from the vehicle, lateral distance of the target object from the vehicle, longitudinal speed, lateral speed, longitudinal acceleration, and lateral acceleration.

[0021] Optionally, the field of view image of the lateral region in front of the vehicle is acquired, comprising:

[0022] The lateral region image when the field of view angle of the vehicle camera in front of the vehicle is at least 100 degrees is acquired as the field of view image.

[0023] In a second aspect, an embodiment of the present application further provides a target object identification processing device, which comprises:

[0024] A field of view image acquisition module is configured to acquire a field of view image of a lateral region in front of the vehicle.

[0025] A target object identification module is configured to determine a region of interest of the field of view image according to the field of view angle of the vehicle, and identify a target object in the region of interest.

[0026] a mobile data output module, configured to determine mobile data of the target object according to position information of the vehicle and the target object, and output the mobile data.

[0027] In a third aspect, an electronic device is provided, and the device includes:

[0028] one or more processors;

[0029] a storage device configured to store one or more programs,

[0030] when the one or more programs are executed by the one or more processors, the one or more processors implement a target object identification processing method as described in any of the embodiments of the present application.

[0031] In a fourth aspect, a computer readable storage medium is provided, and the medium stores a computer program, which, when executed by a processor, implements a target object identification processing method as described in any of the embodiments of the present application.

[0032] The technical solution of the embodiments of the present application acquires a field of view image of a transverse region in front of a vehicle, determines a region of interest of the field of view image according to a field of view angle of the vehicle, identifies a target object in the region of interest, determines mobile data of the target object according to position information of the vehicle and the target object, and outputs the mobile data, thereby solving the problem of vehicle driving safety, realizing targeted identification processing of objects in the region of interest in front of the vehicle, reducing the region of identification processing, thereby reducing the amount of calculation and saving resources. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 is a flowchart of a target object identification processing method provided by the embodiments of the present application;

[0034] Figure 2 is a schematic diagram of a region of interest provided by the embodiments of the present application;

[0035] Figure 3 is a flowchart of another target object identification processing method provided by the embodiments of the present application;

[0036] Figure 4 is a structural schematic diagram of a target object identification processing device provided by the embodiments of the present application;

[0037] Figure 5 is a structural schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0038] The application will be described in further detail below with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not to be used to limit the application. In addition, it should be noted that only the parts related to the application are shown in the drawings for ease of description.

[0039] Figure 1 is a flowchart of a target object recognition processing method provided by an embodiment of the application. The embodiment can be applied to recognition processing of a transverse object in front of a vehicle to ensure the safety of vehicle driving. The method can be executed by a target object recognition processing device, which can be implemented in software and / or hardware and integrated in an electronic device such as a controller of a vehicle, as shown in FIG. 1. The method specifically includes the following steps. Figure 1

[0040] Step 110: Obtain a field-of-view image of a transverse region in front of the vehicle.

[0041] In the embodiment of the application, the field-of-view image of the transverse region in front of the vehicle can be obtained to recognize the transverse object on the road, so as to prompt the driver to drive safely or assist the driver to drive intelligently and improve the safety of vehicle driving.

[0042] In the embodiment of the application, the field-of-view image can be an image formed under the field of view in which the vehicle in front can recognize whether the object is transverse to the road. Specifically, the vehicle can be equipped with a camera device such as a camera, a radar detection device or a vehicle data recorder, etc. The camera device can obtain the field-of-view image at a certain field-of-view angle.

[0043] In an optional embodiment of the application, the field-of-view image of the transverse region in front of the vehicle includes: obtaining a transverse region image of the vehicle camera field-of-view angle of at least 100 degrees as the field-of-view image.

[0044] In the actual research, the inventor found that when the camera field-of-view angle of the vehicle is 100 degrees, the field-of-view range of the camera becomes larger and basically achieves the effect of recognizing the transverse region, which can ensure the safety of vehicle driving. Therefore, in the embodiment of the application, the camera field-of-view angle of the vehicle can be adjusted to be greater than or equal to 100 degrees to ensure that the field-of-view image obtained by the camera can cover the transverse region in front of the vehicle, avoiding the danger caused by the failure to accurately recognize the transverse object on the road.

[0045] Step 120: Determine a region of interest in the field-of-view image according to the field-of-view angle of the vehicle, and recognize a target object in the region of interest.

[0046] ​In the embodiment of the present application, the field of view of the vehicle is increased by identifying the lateral region in front of the vehicle. Specifically, the field of view of the vehicle camera can be increased to increase the field of view of the vehicle. When the field of view of the vehicle is increased, the region involved in the field of view image is increased, and the objects are increased. If all regions and all objects in the field of view image are identified, the calculation amount is increased, and the power consumption and cost of object identification are increased.

[0047] Therefore, in the embodiment of the present application, the region of interest can be determined in the field of view image according to the field of view of the vehicle, and the objects in the region of interest are identified. The region of interest can be one or more. For example, according to the field of view of the vehicle, there can be a region in the field of view image that only affects the driving safety of the vehicle in the lateral direction, and a region that affects the driving safety of the vehicle in the lateral direction and the longitudinal direction. The region that only affects the driving safety of the vehicle in the lateral direction and the region that affects the driving safety of the vehicle in the lateral direction and the longitudinal direction can be different regions of interest. In different regions of interest, the target objects can be different. For example, the target object in the region that only affects the driving safety of the vehicle in the lateral direction can be an object that affects the driving safety of the vehicle in the lateral direction; the target object in the region that affects the driving safety of the vehicle in the lateral direction and the longitudinal direction can be an object that affects the driving safety of the vehicle in the lateral direction and / or the longitudinal direction.

[0048] Specifically, in one optional embodiment of the embodiment of the present application, the region of interest of the field of view image is determined according to the field of view of the vehicle, and the target object is identified in the region of interest, comprising: according to the field of view of the vehicle, the region of the object moving in the lateral direction in the field of view image is taken as a first region of interest, and the region of the object moving in the longitudinal direction is taken as a second region of interest; the first target object is identified in the first region of interest, and the second target object is identified in the second region of interest.

[0049] The region of the object moving in the lateral direction can be the moving region of the object crossing the road. For example, the region of the object moving in the lateral direction can be the zebra crossing and the region around the zebra crossing. The region of the object moving in the longitudinal direction can be the region moving in the same direction as the vehicle. For example, the region of the object moving in the longitudinal direction can be the front and the region around the front. The first target object can be an object with crossing behavior, and the second target object can be an object with crossing behavior and longitudinal moving behavior.

[0050] More specifically, in an optional implementation of the embodiment of the present application, according to the field of view angle of the vehicle, the region in which the object in the field of view image moves laterally is taken as the first region of interest, and the region in which the object moves longitudinally is taken as the second region of interest, comprising: taking the lateral region in the field of view image when the field of view angle of the camera of the vehicle is less than or equal to 52 degrees as the second region of interest; taking the remaining region in the field of view image after removing the second region of interest as the first region of interest.

[0051] In the actual research, the inventor found that the region corresponding to the field of view angle of the camera of the vehicle less than or equal to 52 degrees is usually the object moving longitudinally of the vehicle. When the field of view angle of the camera of the vehicle is greater than 52 degrees, it usually contains the object moving laterally or the object moving laterally and longitudinally. Therefore, in the embodiment of the present application, the field of view image is divided into regions of interest by the field of view angle of 52 degrees of the camera. Specifically, Figure 2 is a schematic diagram of a region of interest provided by the embodiment of the present application. As Figure 2 shown, the field of view image can be divided into regions a, b and c according to the field of view angle of the vehicle. The outer boundary of regions a and c can be the boundary of the field of view range of the camera installed on the vehicle; the inner boundary of regions a and c can be the boundary of the field of view range when the field of view angle of the camera of the vehicle is 52 degrees; the inner boundary of regions a and c constitutes region b inwardly. Region b is the lateral region in the field of view image when the field of view angle of the camera of the vehicle is less than or equal to 52 degrees, that is, it corresponds to the second region of interest. Regions a and c are the remaining regions in the field of view image after removing the second region of interest, that is, they correspond to the first region of interest.

[0052] In an optional implementation of the embodiment of the present application, the first target object includes: pedestrians, two-wheeled vehicles, three-wheeled vehicles and pets; and the second target object includes: pedestrians, two-wheeled vehicles, three-wheeled vehicles, pets and vehicles with three or more wheels.

[0053] As shown in Figure 2 , the object usually moves from region a to region b and then to region c, or from region c to region b and then to region b to cross the road. The objects that usually cross the road include pedestrians, two-wheeled vehicles, three-wheeled vehicles and pets. Therefore, in the embodiment of the present application, the first target object can be the object crossing the road, such as pedestrians, two-wheeled vehicles, three-wheeled vehicles and pets. As Figure 2As shown, the object is usually moved from the area a to the area b, or moved from the area c to the area b to realize the transverse-to-longitudinal movement; or, the longitudinal movement in the area b. Therefore, the object in the area b can be moved transversely or longitudinally, and in order to ensure the safety of the vehicle driving, the object moved transversely or longitudinally in the area b is subjected to the identification processing. Therefore, in the embodiment of the present application, the second target object can be the object moved transversely or longitudinally, for example, the pedestrian, the two-wheeled vehicle, the three-wheeled vehicle, the pet, and the vehicle with the number of wheels more than three.

[0054] In step 130, the movement data of the target object is determined according to the position information of the vehicle and the target object, and the movement data is outputted.

[0055] The movement data can be the data which can affect the safety of the vehicle driving. For example, the movement data can include the distance information and the speed information, etc. The determination of the movement data can be various, for example, the calculation according to the position information and the time information, or the acquisition through the speed detection device, etc., which is not limited in the embodiment of the present application.

[0056] In an optional embodiment of the present application, the movement data of the target object is determined according to the position information of the vehicle and the target object, and the movement data is outputted, including: the movement data of the first target object in the first area of interest is determined according to the position information of the vehicle and the target object; the movement data of the second target object in the second area of interest is determined according to the position information of the vehicle and the target object.

[0057] For the first target object in the first area of interest, the movement data thereof needs to be identified and determined, and for the object other than the first target object in the first area of interest, for example, the car or the truck, etc., only the tracking is needed, and the movement data thereof is not determined, so that the amount of data to be calculated can be reduced, and the effect of saving the energy and the cost can be achieved. For the second target object in the second area of interest, the movement data thereof can be determined, so as to ensure the safety of the vehicle driving.

[0058] In an optional embodiment of the present application, the movement data includes at least one of the following: the object type, the longitudinal distance of the target object from the vehicle, the transverse distance of the target object from the vehicle, the longitudinal speed, the transverse speed, the longitudinal acceleration, and the transverse acceleration.

[0059] Wherein, the target object can be pre-trained for target perception, so that the camera or the controller in the vehicle can recognize the related target and classify it to determine the object type. The longitudinal distance and the lateral distance can be determined according to the field of view image, or can be determined according to the distance detection device, and the embodiments of the present application do not limit the same. The longitudinal speed and the lateral speed can be calculated in real time according to the distance information and the time information. The longitudinal acceleration and the lateral acceleration can be calculated in real time according to the speed information and the time information.

[0060] The technical scheme of the embodiment, by acquiring the field of view image of the transverse region in front of the vehicle; determining the region of interest of the field of view image according to the field of view angle of the vehicle, and recognizing the target object in the region of interest; determining the movement data of the target object according to the position information of the vehicle and the target object, and outputting the movement data, solves the safety problem of vehicle driving, realizes the identification processing of the object in the region of interest in front of the vehicle, can reduce the identification processing area, thereby reducing the calculation amount and saving the resource effect.

[0061] Figure 3 is a flowchart of another target object identification processing method provided by the embodiments of the present application. As shown in Figure 3 , one specific use process of the embodiments of the present application can be: training the target object for target perception, so that the camera can recognize the target such as car, truck, bicycle and pedestrian. The transverse region in front of the vehicle is divided into regions. Specifically, the transverse region in front of the vehicle can be divided into a plurality of regions according to the longitudinal distance and the lateral distance. Figure 2The shown region of interest is divided into region a, region b and region c according to the camera field of view range boundary and the 52-degree field of view range boundary. Different target objects are identified and information is processed for different field of view regions. Specifically, the target objects identified in region a, region b and region c are classified, such as being divided into cars, trucks, bicycles, pedestrians, etc. In region a and region c, only the information of bicycles and pedestrians can be focused on, and only the distance and speed of bicycles and pedestrians are calculated. Specifically, the object types, longitudinal distance, lateral distance, longitudinal speed, lateral speed, longitudinal acceleration and lateral acceleration of bicycles and pedestrians in region a and region c can be determined. For cars, trucks, etc. in region a and region c, no specific information calculation output is performed, only continuous tracking is performed, and when the car or truck cuts into region b, the distance and speed information is calculated. The information of the objects in region b all have an impact on the driving safety of the vehicle, and the distance and speed related information of the objects such as cars, trucks, bicycles and pedestrians in region b can be calculated. Finally, the calculated distance and speed information can be output to prompt the driver to drive safely. Among them, in region a and region c, only the related information of bicycles and pedestrians can be output; in region b, the information of cars, trucks, bicycles and pedestrians can be output. Different target recognition and information processing effects can be achieved for different objects, and calculation resources can be saved.

[0062] Figure 4 is a structural schematic diagram of a target object identification processing device provided by an embodiment of the present application. In combination with Figure 4 The device comprises a field of view image acquisition module 410, a target object identification module 420 and a movement data output module 430. Among them:

[0063] The field of view image acquisition module 410 is configured to acquire a field of view image of a lateral region in front of the vehicle;

[0064] The target object identification module 420 is configured to determine a region of interest of the field of view image according to a field of view angle of the vehicle, and identify a target object in the region of interest;

[0065] The movement data output module 430 is configured to determine movement data of the target object according to position information of the vehicle and the target object, and output the movement data.

[0066] Optionally, the target object identification module 420 comprises:

[0067] The region of interest determination unit is configured to determine a first region of interest as a region in which objects move laterally in the field of view image according to the field of view angle of the vehicle, and determine a second region of interest as a region in which objects move longitudinally;

[0068] The target object recognition unit is configured to recognize a first target object in a first region of interest and recognize a second target object in a second region of interest.

[0069] Optionally, the region of interest determination unit comprises:

[0070] The second region of interest determination sub-unit is configured to determine a lateral region in the field of view image when the field of view angle of the vehicle camera is less than or equal to 52 degrees as the second region of interest.

[0071] The first region of interest determination sub-unit is configured to determine a remaining region in the field of view image after removing the second region of interest as the first region of interest.

[0072] Optionally, the first target object comprises a pedestrian, a two-wheeled vehicle, a three-wheeled vehicle, and a pet.

[0073] The second target object comprises a pedestrian, a two-wheeled vehicle, a three-wheeled vehicle, a pet, and a vehicle with three or more wheels.

[0074] Optionally, the movement data output module 430 comprises:

[0075] The first movement data determination unit is configured to determine movement data of the first target object in the first region of interest according to the position information of the vehicle and the target object.

[0076] The second movement data determination unit is configured to determine movement data of the second target object in the second region of interest according to the position information of the vehicle and the target object.

[0077] Optionally, the movement data comprises at least one of the following: an object type, a longitudinal distance of the target object from the vehicle, a lateral distance of the target object from the vehicle, a longitudinal speed, a lateral speed, a longitudinal acceleration, and a lateral acceleration.

[0078] Optionally, the field of view image acquisition module 410 comprises:

[0079] The field of view image acquisition unit is configured to acquire a lateral region image of the vehicle in front of the vehicle when the field of view angle of the vehicle camera is at least 100 degrees as the field of view image.

[0080] The target object recognition processing device provided by the embodiments of the present application can perform the target object recognition processing method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0081] Figure 5 is a structural schematic diagram of an electronic device provided by an embodiment of the present application, as shown in the figure, the device comprises: Figure 5

[0082] ​One or more processors 510, Figure 5 Take the 510 processor as an example;

[0083] Memory 520;

[0084] The device may also include an input device 530 and an output device 540.

[0085] The processor 510, memory 520, input device 530, and output device 540 in the device can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0086] Memory 520, as a non-transitory computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to a target object recognition and processing method in an embodiment of the present invention (e.g., attached). Figure 4 The illustrated module includes a field-of-view image acquisition module 410, a target object recognition module 420, and a motion data output module 430. The processor 510 executes various functional applications and data processing of the computer device by running software programs, instructions, and modules stored in the memory 520, thereby implementing a target object recognition processing method according to the above method embodiment.

[0087] Acquire a field-of-view image of the lateral area in front of the vehicle;

[0088] Based on the vehicle's field of view angle, the region of interest in the field of view image is determined, and the target object is identified in the region of interest;

[0089] Based on the position information of the vehicle and the target object, the movement data of the target object is determined and output.

[0090] The memory 520 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 520 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 520 may optionally include memory remotely located relative to the processor 510, and these remote memories can be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0091] The input device 530 can be used to receive inputted digital or character information, and to generate key signal input related to user settings and function control of the computer device. The output device 540 can include a display device such as a display screen.

[0092] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the target object identification processing method provided by the embodiment of the present application.

[0093] An image of a field of view of a lateral region in front of the vehicle is acquired;

[0094] A region of interest of the image of the field of view is determined according to a field of view angle of the vehicle, and a target object is identified in the region of interest;

[0095] The movement data of the target object is determined according to position information of the vehicle and the target object, and the movement data is output.

[0096] Any combination of one or more computer readable medium can be employed. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, the computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0097] A computer readable signal medium can include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal can take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0098] Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0099] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0100] Note that, as previously discussed, the above merely describes a few exemplary embodiments of the present application and the principles of technology used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, modifications and substitutions can be made by those skilled in the art without departing from the scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A recognition processing method of a target object, characterized by, The method comprises: acquiring a field of view image of a lateral region in front of the vehicle; regarding a lateral region in the field of view image when the field of view angle of the camera of the vehicle is less than or equal to 52 degrees as a second region of interest; regarding a remaining region in the field of view image after removing the second region of interest as a first region of interest; identifying a first target object in the first region of interest and a second target object in the second region of interest; determining movement data of the target object according to the position information of the vehicle and the target object, and outputting the movement data; wherein the first target object is an object crossing the road, and the second target object is an object moving laterally or longitudinally; only determining the movement data of pedestrians, two-wheeled vehicles, three-wheeled vehicles and pets in the first region of interest, and only tracking the vehicles with more than three wheels without determining the movement data of the vehicles with more than three wheels; and determining the movement data of the vehicles with more than three wheels again when the vehicles with more than three wheels switch to the second region of interest.

2. The method of claim 1, wherein, The first target object comprises pedestrians, two-wheeled vehicles, three-wheeled vehicles and pets. The second target object comprises pedestrians, two-wheeled vehicles, three-wheeled vehicles, pets and vehicles with more than three wheels.

3. The method of claim 1, wherein, Determining the movement data of the target object according to the position information of the vehicle and the target object, and outputting the movement data, comprises: determining the movement data of the first target object in the first region of interest according to the position information of the vehicle and the target object; determining the movement data of the second target object in the second region of interest according to the position information of the vehicle and the target object.

4. The method of claim 1, wherein, The movement data comprises at least one of the following: object type, longitudinal distance of the target object from the vehicle, lateral distance of the target object from the vehicle, longitudinal speed, lateral speed, longitudinal acceleration and lateral acceleration.

5. The method according to any one of claims 1 to 4, characterized in that, Acquiring a field of view image of a lateral region in front of the vehicle comprises: acquiring a lateral region image when the field of view angle of the camera of the vehicle in front of the vehicle is at least 100 degrees as the field of view image.

6. An identification processing apparatus of a target object, characterized by comprising: It comprises: a field of view image acquisition module for acquiring a field of view image of a lateral region in front of the vehicle; a target object identification module for determining a region of interest of the field of view image according to the field of view angle of the vehicle, and identifying a target object in the region of interest; a movement data output module for determining movement data of the target object according to the position information of the vehicle and the target object, and outputting the movement data; wherein the target object identification module comprises: a region of interest determination unit for regarding a lateral movement region of an object in the field of view image as a first region of interest, and regarding a longitudinal movement region of the object as a second region of interest according to the field of view angle of the vehicle; a target object identification unit for identifying a first target object in the first region of interest and a second target object in the second region of interest; the region of interest determination unit comprises: a second region of interest determination subunit for regarding a lateral region in the field of view image when the field of view angle of the camera of the vehicle is less than or equal to 52 degrees as a second region of interest; The first interested region determining sub-unit is configured to take the remaining region of the field of view image after removing the second interested region as the first interested region. The first target object is an object crossing the road, and the second target object is an object moving laterally or longitudinally. The device is configured to determine the moving data of only pedestrians, two-wheeled vehicles, three-wheeled vehicles and pets in the first interested region, and to track only the vehicles with three or more wheels without determining the moving data of the vehicles with three or more wheels; and when the vehicles with three or more wheels switch to the second interested region, the moving data of the vehicles with three or more wheels is determined again.

7. An electronic device, comprising: The device comprises: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-5.

Images