Vehicle control method and device, electronic equipment and computer readable medium

Abstract

Embodiments of the present disclosure disclose a vehicle control method, device, electronic equipment and computer readable medium. A specific embodiment of the method comprises: obtaining a photographed image of an obstacle vehicle corresponding to a target vehicle; identifying a vehicle type of the obstacle vehicle according to the photographed image; determining wheel radius information of the obstacle vehicle according to the vehicle type; performing wheel center point detection on the photographed image to obtain a wheel center point coordinate set; generating a wheel center point three-dimensional coordinate set corresponding to the wheel center point coordinate set in a vehicle body coordinate system of the target vehicle according to the wheel center point coordinate set and the wheel radius information; generating a wheel heading vector corresponding to the obstacle vehicle according to the wheel center point three-dimensional coordinate set; and controlling the target vehicle to travel according to the wheel heading vector. The embodiment improves the accuracy of the determined vehicle orientation and driving safety.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more particularly to vehicle control methods, apparatus, electronic devices, and computer-readable media. Background Technology

[0002] Determining vehicle orientation is crucial for understanding vehicle intent. Currently, the common method for determining vehicle orientation is to input an image into a neural network to detect the wheel outlines and wheel contact points. The wheel outlines primarily assist in determining wheel contact points and wheel direction; while the wheel contact points are mainly used for estimating vehicle orientation. For two wheel contact points on the same side of the vehicle, the direction of the line connecting them is determined as the vehicle orientation.

[0003] However, the inventors discovered that when using the above method to determine vehicle orientation, the following technical problems often arise:

[0004] First, in scenarios with uneven road surfaces such as slopes, the wheel contact point is easily obscured by the road surface, making it impossible to identify the wheel contact point or identifying the wrong wheel contact point. This results in a low accuracy rate in determining the vehicle's orientation, leading to poor driving safety. When camera distortion is large, the position of the wheel contact point in the image may not be directly under the wheel. This labeling error will be transmitted to the neural network, causing the trained neural network to also have certain errors, further resulting in a low accuracy rate in determining the vehicle's orientation and poor driving safety.

[0005] Second, determining the vehicle's orientation solely based on the wheel's contact point without considering the influence of the wheel's center point further leads to a lower accuracy rate in determining the vehicle's orientation and poorer driving safety.

[0006] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0008] Some embodiments of this disclosure provide vehicle control methods, apparatuses, electronic devices, and computer-readable media to address one or more of the technical problems mentioned in the background section above.

[0009] In a first aspect, some embodiments of this disclosure provide a vehicle control method, the method comprising: acquiring a photographed image of an obstacle vehicle corresponding to a target vehicle; identifying the vehicle type of the obstacle vehicle based on the photographed image; determining the wheel radius information of the obstacle vehicle based on the vehicle type; detecting the wheel center points in the photographed image to obtain a set of wheel center point coordinates; generating a three-dimensional coordinate set of wheel center points corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle based on the set of wheel center point coordinates and the wheel radius information; generating a wheel heading vector corresponding to the obstacle vehicle based on the three-dimensional coordinate set of wheel center points; and controlling the target vehicle to travel based on the wheel heading vector.

[0010] Secondly, some embodiments of this disclosure provide a vehicle control device, comprising: an acquisition unit configured to acquire a captured image of an obstacle vehicle corresponding to a target vehicle; an identification unit configured to identify the vehicle type of the obstacle vehicle based on the captured image; a determination unit configured to determine the wheel radius information of the obstacle vehicle based on the vehicle type; a detection unit configured to detect the wheel center points in the captured image to obtain a set of wheel center point coordinates; a first generation unit configured to generate a set of three-dimensional wheel center point coordinates corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle based on the set of wheel center point coordinates and the wheel radius information; a second generation unit configured to generate a wheel heading vector corresponding to the obstacle vehicle based on the set of three-dimensional wheel center point coordinates; and a control unit configured to control the target vehicle to travel based on the wheel heading vector.

[0011] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0012] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0013] The various embodiments of this disclosure have the following beneficial effects: the vehicle control methods of some embodiments of this disclosure improve the accuracy of the determined vehicle orientation and driving safety. Specifically, the reasons for the low accuracy of the determined vehicle orientation and poor driving safety are as follows: in scenarios with uneven road surfaces such as slopes, the wheel contact point is easily obscured by the road surface, resulting in the inability to identify the wheel contact point or the identification of an incorrect wheel contact point, leading to a low accuracy of the determined vehicle orientation and thus poor driving safety; when the camera distortion is large, the position of the wheel contact point in the image is not necessarily directly below the wheel. This labeling error will be transmitted to the neural network, causing the trained neural network to also have certain errors, further resulting in a low accuracy of the determined vehicle orientation and poor driving safety. Based on this, the vehicle control method of some embodiments of this disclosure first acquires an image of an obstacle vehicle corresponding to the target vehicle. Then, based on the acquired image, the vehicle type of the obstacle vehicle is identified. Based on the vehicle type, the wheel radius information of the obstacle vehicle is determined. Thus, the wheel radius information of the obstacle vehicle can be determined by the identified vehicle type. Next, wheel center point detection is performed on the captured images to obtain a set of wheel center point coordinates. This allows identification of the center points of each wheel of the obstacle vehicle in the captured images. Then, based on the wheel center point coordinate set and the wheel radius information, a set of three-dimensional coordinates of the wheel center points corresponding to the aforementioned wheel center point coordinate set is generated in the vehicle coordinate system of the target vehicle. This allows the determination of the three-dimensional coordinates of each wheel center point in the vehicle coordinate system of the target vehicle based on the wheel radius constraint. Next, a wheel heading vector corresponding to the obstacle vehicle is generated based on the aforementioned three-dimensional coordinate set of wheel center points. This allows the determination of the wheel heading vector, which characterizes the heading of the obstacle vehicle, based on the three-dimensional coordinates of each wheel center point in the vehicle coordinate system of the target vehicle. Finally, the target vehicle is controlled based on the aforementioned wheel heading vector. This allows for automatic control of the target vehicle's movement based on the wheel heading vector characterizing the obstacle vehicle's heading. Because the method of determining the vehicle's heading by directly identifying the wheel contact points is not used, but rather by determining the three-dimensional coordinates of the wheel center points, the problem of road surface obstruction can be avoided. Furthermore, because the three-dimensional coordinates of each wheel's center point in the target vehicle's coordinate system are determined based on the wheel radius information, corrections can be made under the constraint of the wheel radius, reducing recognition errors. This improves the accuracy of the determined vehicle orientation and driving safety. Attached Figure Description

[0014] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0015] Figure 1 This is a flowchart of some embodiments of the vehicle control method according to the present disclosure;

[0016] Figure 2 This is a schematic diagram of the structure of some embodiments of the vehicle control device according to the present disclosure;

[0017] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0020] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0021] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0022] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0023] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] Figure 1 A flow 100 of some embodiments of a vehicle control method according to the present disclosure is shown. The vehicle control method includes the following steps:

[0025] Step 101: Obtain images of the obstacle vehicles corresponding to the target vehicle.

[0026] In some embodiments, the executing entity of the vehicle control method (e.g., a computing device) can control an associated camera to capture images of obstacle vehicles corresponding to the target vehicle via a wired or wireless connection. The target vehicle can be the current vehicle. The camera can be a camera positioned on any side of the target vehicle. The obstacle vehicle can be another vehicle affecting the movement of the target vehicle. The captured images can be two-dimensional images captured by the camera. It should be noted that the wireless connection method can include, but is not limited to, 3G / 4G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future known wireless connection methods. The executing entity can be the vehicle-mounted terminal of the target vehicle.

[0027] Step 102: Identify the vehicle type of the obstacle vehicle based on the captured image.

[0028] In some embodiments, the executing entity can identify the vehicle type of the obstacle vehicle based on the captured image. The vehicle type can represent the vehicle model. In practice, the executing entity can input the captured image into a pre-trained vehicle type recognition model to obtain the vehicle type of the obstacle vehicle. The vehicle type recognition model can be a neural network model that takes the vehicle image as input data and the vehicle type as output data. For example, the neural network model can be a convolutional neural network.

[0029] Step 103: Determine the wheel radius information of the obstacle vehicle based on the vehicle type.

[0030] In some embodiments, the executing entity may determine the wheel radius information of the obstacle vehicle based on the vehicle type. The wheel radius information may be a range to which the wheel radius belongs. In practice, the executing entity may determine the wheel radius information of the obstacle vehicle based on the vehicle type in various ways.

[0031] In some optional implementations of certain embodiments, firstly, the executing entity can select preset wheel radius comparison information corresponding to the vehicle type from a preset wheel radius comparison information set as the target wheel radius comparison information. The preset wheel radius comparison information set can be a pre-defined set of comparison information used to find wheel radii based on vehicle type. The preset wheel radius comparison information in the preset wheel radius comparison information set can include a preset vehicle type and a preset wheel radius. In practice, the executing entity can select preset wheel radius comparison information from the preset wheel radius comparison information set that includes a preset vehicle type identical to the vehicle type as the target wheel radius comparison information. Then, the preset wheel radius included in the target wheel radius comparison information can be determined as the wheel radius information of the obstacle vehicle.

[0032] Step 104: Detect the center point of the wheel in the captured image to obtain the coordinate set of the center point of the wheel.

[0033] In some embodiments, the execution entity can perform wheel center point detection on the captured image to obtain a set of wheel center point coordinates. In practice, the execution entity can input the captured image into a pre-trained wheel center point recognition model to obtain the set of wheel center point coordinates. The wheel center point recognition model can be a neural network model that takes the vehicle image as input data and the identified wheel center point coordinates as output data. For example, the neural network model can be a convolutional neural network. Here, the wheel center point coordinates can be two-dimensional coordinates in the image coordinate system.

[0034] Step 105: Based on the set of wheel center point coordinates and wheel radius information, generate a three-dimensional coordinate set of the wheel center point corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle.

[0035] In some embodiments, the execution entity can generate a set of three-dimensional coordinates of the wheel center points corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle, based on the set of wheel center point coordinates and the wheel radius information. In practice, the execution entity can generate a set of three-dimensional coordinates of the wheel center points corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle through various methods, based on the set of wheel center point coordinates and the wheel radius information.

[0036] In some optional implementations of certain embodiments, firstly, the executing entity can determine the number of wheel center point coordinates included in the wheel center point coordinate set as the wheel center point coordinate quantity. Then, in response to determining that the wheel center point coordinate quantity is a preset value, it determines whether each wheel center point coordinate in the wheel center point coordinate set satisfies a preset lateral condition. The preset value can be a pre-defined number of wheels on one side of the vehicle. For example, the preset value can be 2. The preset lateral condition can be that each wheel center point coordinate is the wheel center point coordinate of each wheel on the same side of the obstacle vehicle. Here, when the acute angle between the line connecting two wheel center point coordinates and the top contour line of the obstacle vehicle is less than a preset angle, the two wheel center point coordinates can be considered as the wheel center point coordinates of two wheels on the same side of the obstacle vehicle. For example, the preset angle can be 10 degrees. Afterwards, in response to determining that each wheel center point coordinate satisfies the preset lateral condition, the wheel center point coordinate set and the wheel radius information are input to a pre-constructed three-dimensional coordinate constraint function to obtain a three-dimensional coordinate constraint equation. The aforementioned three-dimensional coordinate constraint function may include a ground manifold constraint function. This three-dimensional coordinate constraint function can be a function that constrains the magnitude of the three-dimensional coordinates. The aforementioned ground manifold constraint function can be a function that constrains the relationship between lane line points and the ground curve. For example, the aforementioned ground manifold constraint function can be a constraint function that characterizes all lane line points as lying on the ground curve. Here, the ground curve can be represented by a curve equation. As an example, the aforementioned three-dimensional coordinate constraint function can be:

[0037]

[0038]

[0039]

[0040]

[0041]

[0042] in, This represents the three-dimensional coordinates of the wheel's center point. This indicates the three-dimensional coordinates of the center point of the other wheel. This represents the three-dimensional coordinates of the wheel's contact point. This indicates the three-dimensional coordinates of the other wheel's contact point. b p1 represents the three-dimensional coordinate variable of the wheel's center point. b p2 represents the three-dimensional coordinate variable of the center point of the other wheel. b p3 represents the three-dimensional coordinate variable of the wheel contact point. bp4 represents the three-dimensional coordinate variables of the other wheel's contact point. λ1, λ2, and λ3 represent the respective weighting coefficients. M represents the ground manifold constraint function. k () represents the equation of the ground curve. This represents the three-dimensional coordinates in the vehicle coordinate system. This represents the gradient vector of the curve equation of the ground curve in the vehicle coordinate system. ∑1, These are the covariance matrices representing the errors detected in the captured images of the coordinates of the two wheel center points. e1 represents the error in the gradient vector of the curve equation between the wheel center point, the wheel contact point, and the ground curve. e2 represents the error between the wheel contact point and the ground curve. e3 represents the reprojection error of the wheel center point. This represents the transformation function that converts the coordinates of a point from the vehicle coordinate system to the image coordinate system. Here, i represents the image coordinate system, b represents the vehicle coordinate system, and k represents the frame number of the currently captured image. i p1 represents the coordinates of the center point of a wheel. i p2 represents the coordinates of the center point of the other wheel. [r min r max The symbol ] indicates the wheel radius information, that is, the range to which the wheel radius belongs.

[0043] Finally, the above three-dimensional coordinate constraint equations are solved to obtain the set of three-dimensional coordinates of the wheel center points corresponding to the above set of wheel center point coordinates. In practice, the above-mentioned execution entity can use a solver to solve the above three-dimensional coordinate constraint equations to obtain the set of three-dimensional coordinates of the wheel center points corresponding to the above set of wheel center point coordinates.

[0044] Optionally, the above-mentioned three-dimensional coordinate constraint function can take the set of three-dimensional coordinates of the wheel center point and the set of three-dimensional coordinates of the wheel contact point corresponding to the set of three-dimensional coordinates of the wheel center point as output variables.

[0045] In some optional implementations of certain embodiments, the execution entity can solve the three-dimensional coordinate constraint equations to obtain the three-dimensional coordinate set of the wheel center point and the three-dimensional coordinate set of the wheel contact point corresponding to the coordinate set of the wheel center point.

[0046] Optionally, the execution entity may, in response to determining that the number of wheel center point coordinates is less than the preset value, reacquire images of the obstacle vehicle to re-detect the wheel center points. Thus, when the number of wheel center point coordinates is insufficient to determine the wheel heading vector, images of the obstacle vehicle can be reacquired.

[0047] Step 106: Generate the wheel heading vector of the corresponding obstacle vehicle based on the three-dimensional coordinate set of the wheel center point.

[0048] In some embodiments, the execution entity can generate a wheel heading vector corresponding to the obstacle vehicle based on the three-dimensional coordinate set of the wheel center point.

[0049] In some optional implementations of certain embodiments, firstly, the executing entity can determine the three-dimensional coordinates of the wheel center points corresponding to the front position of the obstacle vehicle from the set of three-dimensional coordinates of the wheel center points as the three-dimensional coordinates of the front wheel center points. Here, the three-dimensional coordinates of the wheel center points corresponding to the front position of the obstacle vehicle can be the three-dimensional coordinates of the wheel center points closer to the front position of the obstacle vehicle. Then, the three-dimensional coordinates of the wheel center points corresponding to the rear position of the obstacle vehicle from the set of three-dimensional coordinates of the wheel center points can be determined as the three-dimensional coordinates of the rear wheel center points. Here, the three-dimensional coordinates of the wheel center points corresponding to the rear position of the obstacle vehicle can be the three-dimensional coordinates of the wheel center points closer to the rear position of the obstacle vehicle. Afterwards, the difference between the three-dimensional coordinates of the rear wheel center points and the three-dimensional coordinates of the front wheel center points can be determined as the wheel heading vector corresponding to the obstacle vehicle.

[0050] In some optional implementations of certain embodiments, firstly, the executing entity can determine the three-dimensional coordinates of the wheel center points corresponding to the front position of the obstacle vehicle from the set of three-dimensional coordinates of the wheel center points as the three-dimensional coordinates of the front wheel center points. Then, it can determine the three-dimensional coordinates of the wheel center points corresponding to the rear position of the obstacle vehicle from the set of three-dimensional coordinates of the wheel center points as the three-dimensional coordinates of the rear wheel center points. Next, the difference between the three-dimensional coordinates of the rear wheel center points and the three-dimensional coordinates of the front wheel center points can be determined as the first wheel heading vector corresponding to the obstacle vehicle. Then, the three-dimensional coordinates of the wheel contact points corresponding to the front position of the obstacle vehicle from the set of three-dimensional coordinates of the wheel contact points can be determined as the three-dimensional coordinates of the front wheel contact points. Next, the three-dimensional coordinates of the wheel contact points corresponding to the rear position of the obstacle vehicle from the set of three-dimensional coordinates of the wheel contact points can be determined as the three-dimensional coordinates of the rear wheel contact points. Finally, the difference between the three-dimensional coordinates of the rear wheel contact points and the three-dimensional coordinates of the front wheel contact points can be determined as the second wheel heading vector corresponding to the obstacle vehicle. Finally, the average of the first wheel heading vector and the second wheel heading vector can be determined as the wheel heading vector corresponding to the obstacle vehicle.

[0051] The above-described technical solution, as an inventive point of this disclosure, solves the second technical problem mentioned in the background art: "Determining vehicle orientation solely through wheel contact points without considering the influence of wheel center points leads to low accuracy in determining vehicle orientation and poor driving safety." Factors leading to low accuracy in determining vehicle orientation and poor driving safety often include: determining vehicle orientation solely through wheel contact points without considering the influence of wheel center points. Solving these factors can improve the accuracy of vehicle orientation and driving safety. To achieve this, this disclosure determines the wheel heading vector from the dimensions of the wheel center point and the wheel contact point by estimating the three-dimensional coordinates of the wheel center point and the three-dimensional coordinates of the wheel contact point, respectively. Then, the average of the wheel heading vectors determined in the two dimensions is used as the wheel heading vector corresponding to the aforementioned obstacle vehicle. Thus, by comprehensively considering the wheel heading vectors in both dimensions, the accuracy of determining vehicle orientation and driving safety are improved.

[0052] Step 107: Control the target vehicle's movement based on the wheel heading vector.

[0053] In some embodiments, the executing entity can control the target vehicle to move based on the wheel heading vector. The executing entity can control the target vehicle to move based on the wheel heading vector in various ways.

[0054] Optionally, the aforementioned obstacle vehicle can be a vehicle traveling parallel to the aforementioned target vehicle. This can be understood as the obstacle vehicle traveling parallel to one side of the aforementioned target vehicle.

[0055] In some optional implementations of certain embodiments, firstly, the executing entity can determine the heading angle of the obstacle vehicle as the angle between the wheel heading vector and the horizontal axis of the vehicle coordinate system. Then, it can determine whether the heading angle is less than a preset angle. For example, the preset angle can be 80 degrees. Next, in response to determining that the heading angle is less than the preset angle, it can determine whether the distance between the obstacle vehicle and the target vehicle is less than a preset distance. Here, the distance between the obstacle vehicle and the target vehicle can be the perpendicular distance between them. For example, the preset distance can be 1.5 meters. Then, in response to determining that the distance between the obstacle vehicle and the target vehicle is less than the preset distance, the deceleration of the target vehicle is determined based on the heading angle. In practice, the executing entity can input the heading angle into a preset deceleration determination function to obtain the deceleration of the target vehicle. Here, the preset deceleration determination function can be a pre-set linear function. The specific setting of the preset deceleration determination function is not limited. Finally, the target vehicle can be controlled to decelerate based on the deceleration. In practice, the aforementioned implementing entity can control the target vehicle to decelerate according to the aforementioned deceleration rate. Therefore, when an obstacle vehicle traveling parallel at close range shows an intention to approach the current vehicle, the current vehicle can be automatically controlled to decelerate.

[0056] The various embodiments of this disclosure have the following beneficial effects: the vehicle control methods of some embodiments of this disclosure improve the accuracy of the determined vehicle orientation and driving safety. Specifically, the reasons for the low accuracy of the determined vehicle orientation and poor driving safety are as follows: in scenarios with uneven road surfaces such as slopes, the wheel contact point is easily obscured by the road surface, resulting in the inability to identify the wheel contact point or the identification of an incorrect wheel contact point, leading to a low accuracy of the determined vehicle orientation and thus poor driving safety; when the camera distortion is large, the position of the wheel contact point in the image is not necessarily directly below the wheel. This labeling error will be transmitted to the neural network, causing the trained neural network to also have certain errors, further resulting in a low accuracy of the determined vehicle orientation and poor driving safety. Based on this, the vehicle control method of some embodiments of this disclosure first acquires an image of an obstacle vehicle corresponding to the target vehicle. Then, based on the acquired image, the vehicle type of the obstacle vehicle is identified. Based on the vehicle type, the wheel radius information of the obstacle vehicle is determined. Thus, the wheel radius information of the obstacle vehicle can be determined by the identified vehicle type. Next, wheel center point detection is performed on the captured images to obtain a set of wheel center point coordinates. This allows identification of the center points of each wheel of the obstacle vehicle in the captured images. Then, based on the wheel center point coordinate set and the wheel radius information, a set of three-dimensional coordinates of the wheel center points corresponding to the aforementioned wheel center point coordinate set is generated in the vehicle coordinate system of the target vehicle. This allows the determination of the three-dimensional coordinates of each wheel center point in the vehicle coordinate system of the target vehicle based on the wheel radius constraint. Next, a wheel heading vector corresponding to the obstacle vehicle is generated based on the aforementioned three-dimensional coordinate set of wheel center points. This allows the determination of the wheel heading vector, which characterizes the heading of the obstacle vehicle, based on the three-dimensional coordinates of each wheel center point in the vehicle coordinate system of the target vehicle. Finally, the target vehicle is controlled based on the aforementioned wheel heading vector. This allows for automatic control of the target vehicle's movement based on the wheel heading vector characterizing the obstacle vehicle's heading. Because the method of determining the vehicle's heading by directly identifying the wheel contact points is not used, but rather by determining the three-dimensional coordinates of the wheel center points, the problem of road surface obstruction can be avoided. Furthermore, because the three-dimensional coordinates of each wheel's center point in the target vehicle's coordinate system are determined based on the wheel radius information, corrections can be made under the constraint of the wheel radius, reducing recognition errors. This improves the accuracy of the determined vehicle orientation and driving safety.

[0057] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a vehicle control device, which are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0058] like Figure 2 As shown, the vehicle control device 200 in some embodiments includes: an acquisition unit 201, an identification unit 202, a determination unit 203, a detection unit 204, a first generation unit 205, a second generation unit 206, and a control unit 207. The acquisition unit 201 is configured to acquire images of obstacle vehicles corresponding to the target vehicle; the identification unit 202 is configured to identify the vehicle type of the obstacle vehicle based on the acquired images; the determination unit 203 is configured to determine the wheel radius information of the obstacle vehicle based on the vehicle type; the detection unit 204 is configured to detect the wheel center points of the acquired images to obtain a set of wheel center point coordinates; the first generation unit 205 is configured to generate a set of three-dimensional wheel center point coordinates corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle based on the set of wheel center point coordinates and the wheel radius information; the second generation unit 206 is configured to generate a wheel heading vector corresponding to the obstacle vehicle based on the set of three-dimensional wheel center point coordinates; and the control unit 207 is configured to control the target vehicle to travel based on the wheel heading vector.

[0059] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0060] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 (e.g., a vehicle terminal) suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0061] like Figure 3 As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0062] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0063] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0064] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0065] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0066] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire a photographed image of an obstacle vehicle corresponding to the target vehicle; identify the vehicle type of the obstacle vehicle based on the photographed image; determine the wheel radius information of the obstacle vehicle based on the vehicle type; detect the wheel center points in the photographed image to obtain a set of wheel center point coordinates; generate a set of three-dimensional wheel center point coordinates corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle based on the set of wheel center point coordinates and the wheel radius information; generate a wheel heading vector corresponding to the obstacle vehicle based on the set of three-dimensional wheel center point coordinates; and control the target vehicle to travel based on the wheel heading vector.

[0067] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0068] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0069] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, an identification unit, a determination unit, a detection unit, a first generation unit, a second generation unit, and a control unit. The names of these units do not necessarily limit the specific unit; for example, an acquisition unit may also be described as "a unit that acquires images of obstacle vehicles corresponding to a target vehicle."

[0070] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0071] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A vehicle control method, comprising: Acquire images of obstacle vehicles corresponding to the target vehicle; Based on the captured images, identify the vehicle type of the obstacle vehicle; Based on the vehicle type, determine the wheel radius information of the obstacle vehicle; The captured image is used to detect the center point of the wheel, and a set of coordinates of the center point of the wheel is obtained; Based on the set of wheel center point coordinates and the wheel radius information, a three-dimensional set of wheel center point coordinates corresponding to the set of wheel center point coordinates is generated in the vehicle coordinate system of the target vehicle. Based on the set of three-dimensional coordinates of the wheel center point, generate the wheel heading vector corresponding to the obstacle vehicle; The target vehicle is controlled to travel based on the wheel heading vector; The step of determining the wheel radius information of the obstacle vehicle based on the vehicle type includes: Select the preset wheel radius comparison information corresponding to the vehicle type from the preset wheel radius comparison information set as the target wheel radius comparison information, wherein the preset wheel radius comparison information in the preset wheel radius comparison information set includes a preset vehicle type and a preset wheel radius; The preset wheel radius included in the target wheel radius comparison information is determined as the wheel radius information of the obstacle vehicle; The step of generating a set of three-dimensional coordinates of the wheel center points corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle, based on the set of wheel center point coordinates and the wheel radius information, includes: The number of wheel center point coordinates included in the set of wheel center point coordinates is defined as the number of wheel center point coordinates. In response to determining that the number of wheel center point coordinates is a preset value, determine whether the coordinates of each wheel center point in the set of wheel center point coordinates meet the preset lateral conditions. In response to determining that the coordinates of the center points of each wheel satisfy the preset lateral condition, the set of wheel center point coordinates and the wheel radius information are input to a pre-constructed three-dimensional coordinate constraint function to obtain a three-dimensional coordinate constraint equation, wherein the three-dimensional coordinate constraint function includes a ground manifold constraint function; Solving the three-dimensional coordinate constraint equations yields the three-dimensional coordinate set of the wheel center point corresponding to the set of wheel center point coordinates. The three-dimensional coordinate constraint function takes the set of three-dimensional coordinates of the wheel center point and the set of three-dimensional coordinates of the wheel contact point corresponding to the set of three-dimensional coordinates of the wheel center point as output variables; and the solution of the three-dimensional coordinate constraint equation includes: Solving the three-dimensional coordinate constraint equations yields the three-dimensional coordinate set of the wheel center point and the three-dimensional coordinate set of the wheel contact point, corresponding to the coordinate set of the wheel center point.

2. The method of claim 1, wherein, The method further includes: In response to determining that the number of wheel center point coordinates is less than the preset value, the image of the obstacle vehicle is reacquired to re-detect the wheel center points.

3. The method of claim 1, wherein, The step of generating the wheel heading vector corresponding to the obstacle vehicle based on the three-dimensional coordinate set of the wheel center point includes: The three-dimensional coordinates of the wheel center point corresponding to the front position of the obstacle vehicle in the three-dimensional coordinate set of the wheel center point are determined as the three-dimensional coordinates of the front wheel center point. The three-dimensional coordinates of the wheel center point corresponding to the rear position of the obstacle vehicle in the three-dimensional coordinate set of the wheel center point are determined as the three-dimensional coordinates of the rear wheel center point. The difference between the three-dimensional coordinates of the center point of the rear wheel and the three-dimensional coordinates of the center point of the front wheel is determined as the wheel heading vector of the obstacle vehicle.

4. The method according to one of claims 1 to 3, wherein The obstacle vehicle is a vehicle that runs parallel to the target vehicle; And controlling the target vehicle's movement based on the wheel heading vector includes: The angle between the wheel heading vector and the horizontal axis of the vehicle coordinate system is determined as the heading angle of the obstacle vehicle. Determine whether the heading angle is less than a preset angle; In response to determining that the heading angle is less than the preset angle, determine whether the distance between the obstacle vehicle and the target vehicle is less than the preset distance; In response to determining that the distance between the obstacle vehicle and the target vehicle is less than the preset distance, the deceleration of the target vehicle is determined based on the heading angle; Based on the deceleration rate, the target vehicle is controlled to slow down.

5. A vehicle control device, comprising: The acquisition unit is configured to acquire images of obstacle vehicles corresponding to the target vehicle; The identification unit is configured to identify the vehicle type of the obstacle vehicle based on the captured image; The determining unit is configured to determine the wheel radius information of the obstacle vehicle according to the vehicle type, including: selecting preset wheel radius comparison information corresponding to the vehicle type from a preset wheel radius comparison information set as target wheel radius comparison information, wherein the preset wheel radius comparison information in the preset wheel radius comparison information set includes a preset vehicle type and a preset wheel radius; and determining the preset wheel radius included in the target wheel radius comparison information as the wheel radius information of the obstacle vehicle. The detection unit is configured to detect the center point of the wheel in the captured image and obtain a set of coordinates of the center point of the wheel. The first generation unit is configured to generate a set of three-dimensional coordinates of wheel centers corresponding to the set of wheel center point coordinates in the vehicle coordinate system of the target vehicle, based on the set of wheel center point coordinates and the wheel radius information. This includes: determining the number of wheel center point coordinates included in the set of wheel center point coordinates as the number of wheel center point coordinates; in response to determining that the number of wheel center point coordinates is a preset value, determining whether each wheel center point coordinate in the set of wheel center point coordinates satisfies a preset lateral condition; in response to determining that each wheel center point coordinate satisfies the preset lateral condition, inputting the set of wheel center point coordinates and the wheel radius information into a pre-constructed three-dimensional coordinate constraint function to obtain a three-dimensional coordinate constraint equation, wherein the three-dimensional coordinate constraint function includes a ground manifold constraint function; and solving the three-dimensional coordinate constraint equation to obtain the set of three-dimensional coordinates of wheel centers corresponding to the set of wheel center point coordinates. The three-dimensional coordinate constraint function takes the three-dimensional coordinate set of the wheel center point and the three-dimensional coordinate set of the wheel contact point corresponding to the three-dimensional coordinate set of the wheel center point as output variables; and the solution of the three-dimensional coordinate constraint equation includes: solving the three-dimensional coordinate constraint equation to obtain the three-dimensional coordinate set of the wheel center point and the three-dimensional coordinate set of the wheel contact point corresponding to the three-dimensional coordinate set of the wheel center point. The second generation unit is configured to generate a wheel heading vector corresponding to the obstacle vehicle based on the three-dimensional coordinate set of the wheel center point. The control unit is configured to control the movement of the target vehicle based on the wheel heading vector.

6. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-4.

7. A computer readable medium having stored thereon a computer program, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images