A driving direction detection method, device, computer equipment and storage medium

Abstract

The present disclosure provides a driving direction detection method, device, computer equipment and storage medium, which obtains the driving image of the surrounding vehicles of the target vehicle during driving; identifies the vehicle to be detected and at least two wheels of the vehicle to be detected from the image; and determines the driving direction of the vehicle to be detected based on the at least two wheels. In this way, the real driving direction of the surrounding vehicles can be effectively detected with high accuracy and good robustness, which is conducive to helping the target vehicle judge the driving conditions of the surrounding vehicles, so as to prepare response strategies in advance, and can effectively reduce the probability of accidents.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a driving direction detection method, device, computer equipment and storage medium. Background Art

[0002] With the development and progress of science and technology, cars have gradually entered more and more families, bringing great convenience to users' travel. In recent years, with the development of autonomous driving and assisted driving technology, people's requirements for driving experience have become higher and higher, and the demand has gradually shifted from L0 assisted driving with alarm function to L1 and L2 assisted driving with added control. Unlike the L0 alarm function, L2 assisted driving requires a more accurate understanding of the distance, speed, direction and intention of surrounding targets, and has higher requirements for perception and recognition.

[0003] In view of this, in autonomous driving, how to effectively and accurately identify the direction of surrounding vehicles has become an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a driving direction detection method, apparatus, computer equipment and storage medium.

[0005] In a first aspect, an embodiment of the present disclosure provides a driving direction detection method, the method comprising:

[0006] Acquire the driving images of the surrounding vehicles of the target vehicle during its driving process;

[0007] Identifying a vehicle to be detected and at least two wheels to be detected of the vehicle to be detected from the image;

[0008] Based on the at least two wheels, a driving direction of the vehicle to be detected is determined.

[0009] In this way, the vehicle's wheels can be identified through the collected images, and the vehicle's driving direction can be detected through the wheels. The vehicle's driving direction can be effectively detected with high accuracy and good robustness. This is helpful in helping the target vehicle judge the driving conditions of surrounding vehicles and prepare response strategies in advance, which can effectively reduce the probability of accidents.

[0010] In an optional implementation, determining the driving direction of the vehicle to be detected based on the at least two wheels includes:

[0011] Determining the attributes of each wheel of the at least two wheels, wherein the attributes of the wheel include whether the wheel is a front wheel or a rear wheel;

[0012] Determining two wheels to be detected among the at least two wheels based on the properties of each wheel;

[0013] Based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected, the driving direction of the vehicle to be detected is determined.

[0014] In this way, the wheels to be detected are screened out by wheel attributes, and the driving direction of the vehicle to be detected is further determined by the information of the wheels to be detected. The driving direction of the vehicle can be determined by targeted screening of wheels with high accuracy and good robustness.

[0015] In an optional implementation manner, identifying the vehicle to be detected and at least two wheels of the vehicle to be detected from the image includes:

[0016] identifying at least one vehicle and a plurality of wheels from the image;

[0017] Determine the position information of each vehicle and the position information of each wheel;

[0018] Based on the position information of each vehicle and the position information of each wheel, a vehicle to be detected in the at least one vehicle and at least two wheels of the vehicle to be detected are determined.

[0019] In this way, by matching at least two wheels belonging to the same vehicle through position information, the wheels corresponding to the vehicle can be accurately detected. This is simple, fast, highly accurate, and robust, which is conducive to improving the accuracy of subsequent detection of the vehicle's driving direction.

[0020] In an optional implementation manner, identifying the vehicle to be detected and at least two wheels of the vehicle to be detected from the image includes:

[0021] Determine a vehicle to be detected in the image;

[0022] At least two wheels of the vehicle to be detected are identified from image content corresponding to the vehicle to be detected in the image.

[0023] In this way, the wheels can be identified by using the image corresponding to the identified vehicle, thereby ensuring the accuracy of the match between the vehicle and the wheels.

[0024] In an optional implementation manner, the following steps are used to determine the properties of at least two wheels of the vehicle to be detected:

[0025] The attribute of each wheel is determined according to the relative position relationship between each wheel of the at least two wheels and the vehicle to be detected.

[0026] In an optional implementation manner, the vehicle to be detected is determined by the following steps:

[0027] A vehicle in the image that has one or more of the following corresponding relationships with the target vehicle is determined as the vehicle to be detected:

[0028] Located in the same lane as the target vehicle, located in an adjacent lane to the target vehicle's lane, located in front of the target vehicle with a distance between the two being less than a first preset distance, located to the side of the target vehicle with a distance between the two being less than a second preset distance, and traveling in the direction of the target vehicle.

[0029] In this way, the vehicles in the surrounding environment that need to be detected in their driving direction can be effectively determined, which is beneficial for reducing the probability of possible traffic accidents by detecting the driving direction of the vehicles and helping the target vehicles to respond in advance.

[0030] In an optional implementation manner, determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected includes:

[0031] The driving direction of the vehicle to be detected is determined based on the preset reference point position information on each wheel to be detected, the attributes of each wheel to be detected, and one or more of the following information:

[0032] The road attributes of the lane where the vehicle to be detected is located, the distance between the vehicle to be detected and the lane line of the lane, and the current position of the vehicle to be detected in the lane.

[0033] In an optional implementation, when the two wheels to be detected include two rear wheels or two front wheels, determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected includes:

[0034] Determining the contact points of the two rear wheels or the two front wheels with the ground, and the midpoint of a first connecting line between the two contact points;

[0035] Determine a perpendicular line with the first connecting line having the midpoint as the intersection point, wherein the perpendicular line is parallel to the ground;

[0036] The direction of the vertical line toward the front of the vehicle to be detected is determined as the driving direction of the vehicle to be detected.

[0037] In an optional embodiment, when the two wheels to be detected include a front wheel and a rear wheel located on the same side of the vehicle to be detected, determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected includes:

[0038] Determining a contact point between the front wheel and the ground, a contact point between the rear wheel and the ground, and a second connecting line from the contact point of the rear wheel toward the contact point of the front wheel;

[0039] The direction of the second connecting line is determined as the driving direction of the vehicle to be detected.

[0040] In an optional implementation manner, the method further includes:

[0041] According to the determined driving direction of the vehicle to be detected, a prompt message is issued or the target vehicle is controlled.

[0042] In a second aspect, an embodiment of the present disclosure further provides a driving direction detection device, the device comprising:

[0043] A driving image acquisition module is used to acquire driving images of surrounding vehicles of the target vehicle during its driving process;

[0044] A vehicle information recognition module, used to recognize a vehicle to be detected and at least two wheels of the vehicle to be detected from the image;

[0045] A driving direction determining module is used to determine the driving direction of the vehicle to be detected based on the at least two wheels.

[0046] In a third aspect, an embodiment of the present disclosure further provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned driving direction detection method are performed.

[0047] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned driving direction detection method are executed.

[0048] The driving direction detection method, device, computer equipment and storage medium provided by the embodiments of the present disclosure obtain driving images of surrounding vehicles of the target vehicle during driving; identify the vehicle to be detected and at least two wheels of the vehicle to be detected from the image; and determine the driving direction of the vehicle to be detected based on the at least two wheels.

[0049] In this way, by detecting the driving direction of surrounding vehicles based on the identified wheels of surrounding vehicles, the real driving direction of surrounding vehicles can be effectively detected with high accuracy and good robustness, which is conducive to helping the target vehicle judge the driving conditions of surrounding vehicles and prepare response strategies in advance, which can effectively reduce the probability of accidents.

[0050] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0052] Figure 1 A flow chart of a driving direction detection method provided by an embodiment of the present disclosure;

[0053] Figure 2 A flow chart of vehicle information recognition in a driving direction detection method provided in an embodiment of the present disclosure;

[0054] Figure 3 A schematic diagram of an image recognition model used in a driving direction detection method provided in an embodiment of the present disclosure;

[0055] Figure 4 A flow chart of vehicle information recognition in another driving direction detection method provided by the present embodiment;

[0056] Figure 5 One of the schematic diagrams of a driving direction detection device provided in an embodiment of the present disclosure;

[0057] Figure 6 A second schematic diagram of a driving direction detection device provided in an embodiment of the present disclosure;

[0058] Figure 7 A schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0060] Research has found that in recent years, with the development of autonomous driving and assisted driving technology, people's requirements for driving experience have become higher and higher. In autonomous driving, how to effectively and accurately identify the direction of surrounding vehicles has become one of the important directions of L2 level assisted driving. At present, most research plans are to give a picture with a vehicle, and train the model by manually marking the direction of the vehicle (for example, dividing the direction into 32 sub-directions) to identify the vehicle direction. However, this method has obvious defects: due to the difference in viewing angle and the distance of the vehicle, it is difficult to accurately mark the direction manually, which will increase the difficulty of network training; the direction marking and use method treats the vehicle as a particle and the actual center of the vehicle as the center of mass, but due to the large difference in vehicle models, there will be a large deviation in converting the obtained direction to the world coordinate system, resulting in inaccurate direction prediction in actual applications, which will cause greater difficulty for downstream control, and even give wrong signals and cause heavy losses.

[0061] Based on the above research, the present disclosure provides a driving direction detection method, which collects driving images of surrounding vehicles of the target vehicle, identifies the wheels of surrounding vehicles from the driving images of surrounding vehicles, and determines the driving directions of surrounding vehicles according to the preset reference point position information on the wheels and the wheel properties. The method can effectively detect the actual driving directions of surrounding vehicles, which is more in line with the actual driving conditions of surrounding vehicles, has high accuracy and good robustness, can effectively reduce the errors existing in marking vehicles as particles, and does not require manual labeling of vehicle directions, which can further reduce the errors in subsequent image recognition caused by the accumulation of errors existing in manual direction labeling, and is conducive to helping the target vehicle judge the driving conditions of surrounding vehicles, so as to prepare response strategies in advance, and can effectively reduce the probability of accidents.

[0062] The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0063] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0064] To facilitate understanding of the present embodiment, a driving direction detection method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the driving direction detection method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the driving direction detection method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0065] The driving direction detection method provided by the embodiment of the present disclosure is described below by taking the execution subject as a terminal device as an example.

[0066] See also Figure 1 , Figure 1 Flow chart of a driving direction detection method provided by an embodiment of the present disclosure. Figure 1 As shown in , the method includes:

[0067] S101: Acquire driving images of surrounding vehicles of a target vehicle during its driving process.

[0068] In this step, during the driving of the target vehicle, driving images of vehicles surrounding the target vehicle may be acquired.

[0069] Among them, the images of surrounding vehicles can be collected by an image acquisition device installed on the target vehicle, or taken by a user riding in the target vehicle using a user terminal, or collected by an image acquisition device set up on the road, and then obtained from an image storage location such as a server through a connection method such as the Internet.

[0070] Among them, the surrounding vehicle driving image can be a panoramic image around the target vehicle, such as a 360-degree panoramic image centered on the target vehicle, or it can be an image of the target vehicle in one or more directions. For example, if the target vehicle is driving in the leftmost lane of the road, then only one or more of the right side image, front image, rear image, right front image and right rear image of the target vehicle can be collected.

[0071] S102: Identify a vehicle to be detected and at least two wheels of the vehicle to be detected from the image.

[0072] In this step, after the image is acquired, the image can be recognized by, for example, an image recognition model or by using image recognition technology to identify the vehicle to be detected and at least two wheels of the vehicle to be detected from the image.

[0073] In actual situations, due to the positional relationship between vehicles during driving, it is generally difficult to see the entire vehicle, and only part of the vehicle can be observed from the relative position. Therefore, most of the vehicles can only be identified partially from the image. For example, ordinary household vehicles generally have only four tires, so generally only two wheels of a vehicle can be seen from an image (for example, from the front perspective, rear perspective, left perspective or right perspective), or three wheels (for example, from the right front perspective, right rear perspective, left front perspective or left rear perspective).

[0074] S103: Determine the driving direction of the vehicle to be detected based on the at least two wheels.

[0075] In this step, after the at least two wheels are identified, the driving direction of the vehicle to be detected can be obtained through relevant information of the at least two wheels, such as position, rotation speed, rotation direction and other factors.

[0076] Specifically, in some possible embodiments, determining the driving direction of the vehicle to be detected based on the at least two wheels may be performed by the following steps:

[0077] S1031. Determine attributes of each wheel of the at least two wheels, wherein the attributes of the wheel include whether the wheel is a front wheel or a rear wheel.

[0078] S1032: Determine two wheels to be detected among the at least two wheels based on the attributes of each wheel.

[0079] S1033. Determine the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected.

[0080] In the above steps, after identifying at least two wheels, the attributes of each wheel can be further determined, for example, by factors such as the position of the wheel, the relative relationship between the wheel and the vehicle body, the steering of the wheel and the extension direction of the road on which the vehicle is located, etc., to determine the wheel attributes, and then two wheels to be detected for judging the driving direction of the vehicle can be determined. The driving direction of the vehicle to be detected is determined by the wheel attributes of each wheel to be detected, combined with the wheel orientation obtained by the preset reference point position information on each wheel to be detected, for example, by comprehensively analyzing the orientations of each wheel, or the orientations between each wheel.

[0081] In a specific application, in step S1031, the following steps may be used to determine the properties of at least two wheels of the vehicle to be detected:

[0082] According to the relative position relationship between each wheel of the at least two wheels and the vehicle to be detected, the attribute of each wheel is determined.

[0083] In this step, the relative position relationship between each wheel to be detected and the vehicle to be detected can be determined by factors such as the position relationship of each wheel to be detected in the image and the position relationship of the vehicle to be detected in the image, thereby obtaining the wheel properties of each wheel to be detected.

[0084] The attributes of the wheel include a front wheel and a rear wheel, that is, the wheel is a front wheel, or the wheel is a rear wheel.

[0085] In some embodiments, the properties of the wheel can be obtained by matching the position information of the wheel with the position information of the vehicle to be detected, or by using the position information of the target vehicle, the position information of the wheel and the relative position relationship between the target vehicle and the vehicle to be detected.

[0086] Among them, the position information of the preset reference point on the wheel to be detected may refer to the position information of the preset reference point on the wheel to be detected. The position of the preset reference point on each wheel to be detected is the same, and its relative position information is also the same. For example, on each wheel, the preset reference point is at the center of each wheel, or at the frontmost point of each wheel, or at the bottommost point of each wheel, etc. In addition, the wheel is dynamic, but in the embodiment of the present disclosure, the preset reference point refers to a static reference point. For example, no matter what position the wheel rotates to, the preset reference point can refer to the reference point of the preset position on the wheel that can be represented in the image at the time corresponding to the captured image.

[0087] The present disclosure provides a driving direction detection method, which can effectively detect the actual driving direction of the surrounding vehicles by collecting driving images of surrounding vehicles of the target vehicle, identifying the wheels of the surrounding vehicles from the driving images of the surrounding vehicles, and determining the driving direction of the surrounding vehicles according to the preset reference point position information on the wheels and the wheel properties. The method has high accuracy and good robustness, can effectively reduce the error existing in marking the vehicle as a particle, and does not need to manually mark the vehicle direction, can further reduce the error in the later image recognition caused by the error accumulation of manual direction marking, is conducive to helping the target vehicle judge the driving conditions of the surrounding vehicles, so as to prepare response strategies in advance, and can effectively reduce the probability of accidents.

[0088] The above S101 to S104 will be described in detail below in conjunction with specific embodiments.

[0089] For the above step S102, please refer to Figure 2 , Figure 2 This is a flow chart of vehicle information recognition in a driving direction detection method provided by the present embodiment. Figure 2 As shown in , step S102 includes:

[0090] S1021: Identify at least one vehicle and a plurality of wheels from the image.

[0091] Among them, to recognize the image, an image recognition model can be constructed through a neural network based on deep learning, and the image can be recognized by the trained image recognition model to obtain at least one vehicle and multiple wheels. In order to reduce the recognition time, improve the recognition speed, etc., the embodiment of the present disclosure can perform the recognition of the vehicle and the recognition of the wheels in parallel.

[0092] Specifically, in order to consider processing speed and model structure deployment, the vehicle recognition and wheel recognition can be performed in parallel, that is, the two tasks can be merged into the same network, such as Figure 3 As shown, Figure 3The schematic diagram of the image recognition model used in the driving direction detection method provided in the embodiment of the present disclosure is a schematic diagram of the image recognition model used in the driving direction detection method provided in the embodiment of the present disclosure. The image recognition model 300 constructed in the embodiment of the present disclosure may include a feature extraction network 310, a vehicle detection network 320 and a wheel detection network 330. The vehicle detection network and the wheel detection network share a common feature extraction network. The vehicle detection network and the wheel detection network may adopt the current mainstream two-stage network (faster-RCNN and other networks) or one-stage network (RetinaNet, FCOS network), etc. This scheme is not limited to the corresponding network structure. ResNet50, ResNet18 and independently designed network structures may also be included in the usage scheme of the embodiment of the present disclosure. Here, the detection scheme and the backbone network structure may be set according to project needs.

[0093] After constructing the above network, we can annotate sample images to mark out the vehicles and wheels in the sample images. For the wheels corresponding to each vehicle, we only annotate the visible wheels. When a wheel is invisible, we do not annotate it. For each wheel, we will mark its attributes as front wheels and rear wheels. When there are multiple wheels on one side of the vehicle, only the frontmost wheel is marked as the front wheel, and the remaining wheels are rear wheels. The constructed network is trained with the annotated sample images, and the trained network is used as an image recognition model to recognize the image, so that recognition results including at least one vehicle and multiple wheels in the image can be obtained in parallel. In addition, the recognition results can also include vehicle information including position information of the vehicle, and wheel information including position information of the wheel.

[0094] S1022: Determine the position information of each vehicle and the position information of each wheel.

[0095] The position information of each vehicle and the position information of each wheel can be determined by obtaining the position information of each vehicle in the image and the position information of each wheel in the image, or by obtaining the position information of each vehicle in the actual scene and the position information of each wheel in the actual scene, as long as the reference system of the vehicle position information is the same as the reference system of the wheel position information.

[0096] Exemplarily, on the premise that the vehicle and the wheels in the image are identified by the image recognition model, the position information corresponding to the identified vehicle and the position information corresponding to the wheels can be obtained from the recognition result.

[0097] S1023: Based on the position information of each vehicle and the position information of each wheel, determine a vehicle to be detected in the at least one vehicle and at least two wheels of the vehicle to be detected.

[0098] In this step, after determining the position information of each vehicle and the position information of each wheel, the vehicle and the wheel can be matched according to a preset distance threshold and range threshold, etc., so as to obtain the vehicle and the wheel corresponding to the vehicle, and then combined with the vehicle's position information, the relevant vehicle to be predicted is determined, so as to obtain the predicted wheel and wheel attributes of the predicted vehicle. Alternatively, the vehicle to be predicted can be determined first, and then the wheel to be predicted and the corresponding wheel attributes can be obtained by matching the position information corresponding to the vehicle to be predicted with the vehicle's position information.

[0099] For the above step S102, please refer to Figure 4 , Figure 4 This is a flow chart of vehicle information recognition in another driving direction detection method provided by the present embodiment. Figure 4 As shown in , step S102 includes:

[0100] S1024: Determine the vehicle to be detected in the image.

[0101] The vehicle to be detected in the image may be determined by recognizing the image through a neural network or the like, thereby identifying the vehicle to be detected.

[0102] S1025: Identify at least two wheels of the vehicle to be detected from image content corresponding to the vehicle to be detected in the image.

[0103] In this step, after the vehicle to be detected in the image is determined, the image content of the vehicle to be detected is further identified to obtain at least two wheels to be detected of the vehicle to be detected.

[0104] In some possible embodiments, for the part of the vehicle to be detected in step S102, the vehicle to be detected can be determined by the following steps:

[0105] A vehicle in the image that has one or more of the following corresponding relationships with the target vehicle is determined as the vehicle to be detected:

[0106] Located in the same lane as the target vehicle, located in an adjacent lane to the target vehicle's lane, located in front of the target vehicle with a distance between the two being less than a first preset distance, located to the side of the target vehicle with a distance between the two being less than a second preset distance, and traveling in the direction of the target vehicle.

[0107] In some possible embodiments, with respect to step S103, step S103 includes:

[0108] The driving direction of the vehicle to be detected is determined based on the preset reference point position information on each wheel to be detected, the attributes of each wheel to be detected, and one or more of the following information:

[0109] The road attributes of the lane where the vehicle to be detected is located, the distance between the vehicle to be detected and the lane line of the lane, and the current position of the vehicle to be detected in the lane.

[0110] In this step, in order to make a more accurate prediction of the orientation of the vehicle to be detected, the above information may be combined based on the preset reference point position information and wheel attributes on each wheel to be detected.

[0111] Exemplary, for example, when the vehicle to be detected on a ramp or other road needs to merge into the road where the target vehicle is located, the real-time driving direction of the vehicle to be detected can be combined; for example, the road where the vehicle to be detected is located is a road that cannot turn. At this time, even if it is determined through the wheels to be detected that the driving direction of the vehicle to be detected intersects with the target vehicle, but in view of the road properties that cannot turn, if the vehicle to be detected has no problems in normal driving, it can be considered that the vehicle to be detected is only fine-tuning the driving state and will still travel in the direction of the road, and the direction of the road can be considered as the driving direction that the vehicle to be detected will still use; for another example, the driving direction of the vehicle to be detected is determined by the position information of the wheels to be detected, but the vehicle to be detected is currently driving on the right lane line, it is far away from the left lane, and the deviation between the detected driving direction and the direction of the lane is not large, then it can also be considered that the vehicle to be detected only needs to be fine-tuned, and its final driving direction is still the direction of the lane.

[0112] In some possible embodiments, when the two wheels to be detected include two rear wheels or two front wheels, with respect to step S103, step S103 includes:

[0113] Determine the contact points of the two rear wheels or the two front wheels with the ground, and the midpoint of the first line between the two contact points; determine a perpendicular line with the first line with the midpoint as the intersection point; determine the direction of the perpendicular line toward the front of the vehicle to be detected as the driving direction of the vehicle to be detected.

[0114] In this step, when it is identified that the two wheels to be inspected of the vehicle to be inspected are two rear wheels or two front wheels, preset reference points on the two rear wheels or front wheels can be determined first, such as the contact points between the rear wheels or the front wheels and the ground, so that a first connecting line can be obtained through the two contact points, and then the direction of the vertical line at the midpoint of the first connecting line is taken as the driving direction of the vehicle to be inspected.

[0115] Furthermore, since the vertical line has no direction, the direction of the vertical line can be determined by combining components such as the front and rear positions of the vehicle to be detected, the direction of the road on which the vehicle to be detected is located, etc., so that the direction of the vertical line can be used as the driving direction of the vehicle to be detected.

[0116] In the disclosed embodiment, the contact point between the rear wheel or the front wheel and the ground is used as an example for explanation, but it is not limited to this. In other embodiments, the center of the hub of the front wheel or the rear wheel may be used as the preset reference point.

[0117] In some possible embodiments, when the two wheels to be detected include a front wheel and a rear wheel located on the same side of the vehicle to be detected, with respect to step S103, step S103 includes:

[0118] Determine the contact point between the front wheel and the ground, the contact point between the rear wheel and the ground, and a second line from the contact point of the rear wheel toward the contact point of the front wheel; and determine the direction of the second line as the driving direction of the vehicle to be detected.

[0119] In this step, when it is identified that the wheels of the vehicle to be detected are a rear wheel and a front wheel on the same side, preset reference points on the rear wheels and the front wheels can be determined first, such as the contact points of the rear wheels and the front wheels with the ground as preset reference points, so that a second connecting line can be obtained through the two contact points, and then the direction of the second connecting line is used as the driving direction of the vehicle to be detected.

[0120] In some possible embodiments, the method further includes:

[0121] According to the determined driving direction of the vehicle to be detected, a prompt message is issued or the target vehicle is controlled.

[0122] In this way, the impact on the target vehicle can be judged based on the determined driving direction of the vehicle to be detected, so that when there is an impact or hidden danger, a prompt message can be issued or the target vehicle can be controlled, which can help improve the driving safety of the target vehicle.

[0123] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0124] Based on the same inventive concept, a driving direction detection device corresponding to the driving direction detection method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned driving direction detection method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0125] See also Figure 5 and Figure 6 , Figure 5 This is one of the schematic diagrams of a driving direction detection device provided in an embodiment of the present disclosure, Figure 6 This is a second schematic diagram of a driving direction detection device provided in an embodiment of the present disclosure. Figure 5 As shown in , the driving direction detection device 500 provided in the embodiment of the present disclosure includes:

[0126] The driving image acquisition module 510 is used to acquire driving images of surrounding vehicles of the target vehicle during its driving process.

[0127] The vehicle information recognition module 520 is used to recognize the vehicle to be detected and at least two wheels of the vehicle to be detected from the image.

[0128] The driving direction determination module 530 is used to determine the driving direction of the vehicle to be detected based on the at least two wheels.

[0129] In an optional implementation manner, the driving direction determination module 530 is specifically configured to:

[0130] Determining the attributes of each wheel of the at least two wheels, wherein the attributes of the wheel include whether the wheel is a front wheel or a rear wheel;

[0131] Determining two wheels to be detected among the at least two wheels based on the properties of each wheel;

[0132] Based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected, the driving direction of the vehicle to be detected is determined.

[0133] In an optional implementation manner, the vehicle information identification module 520 is specifically used to:

[0134] identifying at least one vehicle and a plurality of wheels from the image;

[0135] Determine the position information of each vehicle and the position information of each wheel;

[0136] Based on the position information of each vehicle and the position information of each wheel, a vehicle to be detected in the at least one vehicle and at least two wheels of the vehicle to be detected are determined.

[0137] In an optional implementation manner, the vehicle information identification module 520 is specifically used to:

[0138] Determine a vehicle to be detected in the image;

[0139] Identifying at least two wheels of the vehicle to be detected from image content corresponding to the vehicle to be detected in the image;

[0140] The attribute of each wheel is determined according to the relative position relationship between each wheel of the at least two wheels and the vehicle to be detected.

[0141] In an optional implementation manner, the vehicle information identification module 530 is used to determine the attributes of at least two wheels of the vehicle to be detected by using the following steps:

[0142] The attribute of each wheel is determined according to the relative position relationship between each wheel of the at least two wheels and the vehicle to be detected.

[0143] In an optional implementation manner, the vehicle information identification module 520 is used to determine the vehicle to be detected through the following steps:

[0144] A vehicle in the image that has one or more of the following corresponding relationships with the target vehicle is determined as the vehicle to be detected:

[0145] Located in the same lane as the target vehicle, located in an adjacent lane to the target vehicle's lane, located in front of the target vehicle with a distance between the two being less than a first preset distance, located to the side of the target vehicle with a distance between the two being less than a second preset distance, and traveling in the direction of the target vehicle.

[0146] In an optional implementation manner, the driving direction determination module 530, when used to determine the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected, is specifically used to:

[0147] The driving direction of the vehicle to be detected is determined based on the preset reference point position information on each wheel to be detected, the attributes of each wheel to be detected, and one or more of the following information:

[0148] The road attributes of the lane where the vehicle to be detected is located, the distance between the vehicle to be detected and the lane line of the lane, and the current position of the vehicle to be detected in the lane.

[0149] In an optional implementation manner, when the two wheels to be detected include two rear wheels or two front wheels, the driving direction determination module 530 is used to determine the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected, specifically for:

[0150] Determining the contact points of the two rear wheels or the two front wheels with the ground, and the midpoint of a first connecting line between the two contact points;

[0151] Determine a perpendicular line with the first connecting line with the midpoint as the intersection point;

[0152] The direction of the vertical line toward the front of the vehicle to be detected is determined as the driving direction of the vehicle to be detected.

[0153] In an optional implementation manner, when the two wheels to be detected include a front wheel and a rear wheel located on the same side of the vehicle to be detected, the driving direction determination module 530 is specifically used to determine the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected, and is specifically used to:

[0154] Determining a contact point between the front wheel and the ground, a contact point between the rear wheel and the ground, and a second connecting line from the contact point of the rear wheel toward the contact point of the front wheel;

[0155] The direction of the second connecting line is determined as the driving direction of the vehicle to be detected.

[0156] In an optional implementation, if Figure 6 As shown in , the driving direction detection device 500 also includes:

[0157] The vehicle prompt control module 540 is used to issue a prompt message or control the target vehicle according to the determined driving direction of the vehicle to be detected.

[0158] The driving direction detection device provided by the embodiment of the present disclosure obtains the driving image of the surrounding vehicles of the target vehicle during the driving process; identifies the vehicle to be detected and at least two wheels of the vehicle to be detected from the image, wherein the wheel attributes include the front wheels and the rear wheels; and determines the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected.

[0159] In this way, by detecting the driving direction of surrounding vehicles based on the identified wheels of surrounding vehicles, the real driving direction of surrounding vehicles can be effectively detected with high accuracy and good robustness, which is conducive to helping the target vehicle judge the driving conditions of surrounding vehicles and prepare response strategies in advance, which can effectively reduce the probability of accidents.

[0160] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0161] The present disclosure also provides a computer device 700, such as Figure 7 As shown, it is a schematic diagram of the structure of a computer device 700 provided in an embodiment of the present disclosure, including: a processor 710, a memory 720, and a bus 730. The memory 720 stores machine-readable instructions executable by the processor 710. When the computer device 700 is running, the processor 710 communicates with the memory 720 through the bus 730. When the machine-readable instructions are executed by the processor 710, the steps of the driving direction detection method in the above method embodiment can be executed.

[0162] The specific execution process of the above instructions can refer to the steps of the driving direction detection method described in the embodiment of the present disclosure, which will not be repeated here.

[0163] The embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the driving direction detection method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0164] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK).

[0165] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0168] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0169] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A driving direction detection method, characterized in that: The method comprises: Acquire the driving images of the surrounding vehicles of the target vehicle during its driving process; Identifying a vehicle to be detected and at least two wheels of the vehicle to be detected from the image; Determining the attributes of each wheel of the at least two wheels, wherein the attributes of the wheel include whether the wheel is a front wheel or a rear wheel; Determining two wheels to be detected among the at least two wheels based on the properties of each wheel; Determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected; The determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attribute of each wheel to be detected includes: The driving direction of the vehicle to be detected is determined based on the preset reference point position information on each wheel to be detected, the attributes of each wheel to be detected, and one or more of the following information: The road attributes of the lane where the vehicle to be detected is located, the distance between the vehicle to be detected and the lane line of the lane, and the current position of the vehicle to be detected in the lane.

2. The method according to claim 1, characterized in that The step of identifying the vehicle to be detected and at least two wheels of the vehicle to be detected from the image comprises: identifying at least one vehicle and a plurality of wheels from the image; Determine the position information of each vehicle and the position information of each wheel; Based on the position information of each vehicle and the position information of each wheel, a vehicle to be detected in the at least one vehicle and at least two wheels of the vehicle to be detected are determined.

3. The method according to claim 1, characterized in that The step of identifying the vehicle to be detected and at least two wheels of the vehicle to be detected from the image comprises: Determining a vehicle to be detected in the image; At least two wheels of the vehicle to be detected are identified from image content corresponding to the vehicle to be detected in the image.

4. The method according to claim 1, characterized in that: The following steps are used to determine the properties of at least two wheels of the vehicle to be detected: The attribute of each wheel is determined according to the relative position relationship between each wheel of the at least two wheels and the vehicle to be detected.

5. The method according to any one of claims 1 to 4, characterized in that The vehicle to be detected is determined by the following steps: A vehicle in the image that has one or more of the following corresponding relationships with the target vehicle is determined as the vehicle to be detected: Located in the same lane as the target vehicle, located in an adjacent lane to the target vehicle's lane, located in front of the target vehicle with a distance between the two being less than a first preset distance, located to the side of the target vehicle with a distance between the two being less than a second preset distance, and traveling in the direction of the target vehicle.

6. The method according to any one of claims 1 to 4, characterized in that In the case where the two wheels to be detected include two rear wheels or two front wheels, determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected includes: Determining the contact points of the two rear wheels or the two front wheels with the ground, and the midpoint of a first connecting line between the two contact points; Determine a perpendicular line with the first connecting line having the midpoint as the intersection point, wherein the perpendicular line is parallel to the ground; The direction of the vertical line toward the front of the vehicle to be detected is determined as the driving direction of the vehicle to be detected.

7. The method according to any one of claims 1 to 4, characterized in that In a case where the wheels to be detected include a front wheel and a rear wheel located on the same side of the vehicle to be detected, determining the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected includes: Determining a contact point between the front wheel and the ground, a contact point between the rear wheel and the ground, and a second connecting line from the contact point of the rear wheel toward the contact point of the front wheel; The direction of the second connecting line is determined as the driving direction of the vehicle to be detected.

8. The method according to any one of claims 1 to 4, characterized in that The method further comprises: According to the determined driving direction of the vehicle to be detected, a prompt message is issued or the target vehicle is controlled.

9. A driving direction detection device, characterized in that: The device comprises: A driving image acquisition module is used to acquire driving images of surrounding vehicles of the target vehicle during its driving process; A vehicle information recognition module, used to recognize a vehicle to be detected and at least two wheels of the vehicle to be detected from the image; A driving direction determination module, used to determine the attributes of each wheel of the at least two wheels, wherein the attributes of the wheel include whether the wheel is a front wheel or a rear wheel; based on the attributes of each wheel, determine two wheels to be detected among the at least two wheels; based on the preset reference point position information on each wheel to be detected and the attributes of each wheel to be detected, determine the driving direction of the vehicle to be detected; The driving direction determining module is used to determine the driving direction of the vehicle to be detected based on the preset reference point position information on each wheel to be detected and the attribute of each wheel to be detected, and is specifically used to: The driving direction of the vehicle to be detected is determined based on the preset reference point position information on each wheel to be detected, the attributes of each wheel to be detected, and one or more of the following information: The road attributes of the lane where the vehicle to be detected is located, the distance between the vehicle to be detected and the lane line of the lane, and the current position of the vehicle to be detected in the lane.

10. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the driving direction detection method as described in any one of claims 1 to 8 are performed.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the driving direction detection method as described in any one of claims 1 to 8 are executed.

Images