Method, system and device for preventing tire from being scratched during vehicle parking and storage medium

Abstract

The invention discloses a tire scratch prevention method, system and device during vehicle parking and a storage medium, and the method comprises the steps: obtaining the vehicle speed, gear and positioning information of a target vehicle, and judging whether the target vehicle is in a parking scene or not according to the vehicle speed, gear and positioning information; when the target vehicle is in the parking scene, acquiring environment image information around the target vehicle, and inputting the environment image information into a pre-trained limiter detection model to obtain limiter types and limiter positions of a plurality of parking space limiters; when the parking space limiters are limiters with sharp side edges, whether the tire scratching risk exists or not is judged according to the tire movement track of the target vehicle and the positions of the limiters; when the tire scratching risk exists, early warning information is generated, and a driver is reminded. The method can prevent the driver from scratching the tire during parking, prevents the vehicle appearance and driving safety from being affected, and can be applied to the technical field of vehicle monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle monitoring, and in particular to a method, system, device and storage medium for preventing tires from being scratched when a vehicle is parked. Background Art

[0002] When parking manually, the driver must observe the surroundings for obstacles and the position of the parking stop, and actively control the vehicle's posture to park. Generally, the front of a parking stop is designed as a buffering slope, which will not damage the tire even if it comes into contact with the vehicle's tire. However, the side of the parking stop usually does not come into contact with the vehicle's tire, so its scratch resistance is not considered during the design.

[0003] When the side of the parking limiter is perpendicular to the ground, its side is at right angles to the front, back and top surfaces. Therefore, a sharp right-angled protrusion is formed at the junction of the side, front, back and top surfaces. If the driver deviates during manual parking and causes the tire to contact the side of the parking limiter, the right-angled protrusion on the side edge of the parking limiter may scratch the tire and rim, causing damage to the tire and affecting the vehicle's appearance and driving safety. Summary of the Invention

[0004] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, one purpose of an embodiment of the present invention is to provide a method for preventing tire scratches when parking a vehicle. The method can identify the limiter type and limiter position when the driver performs manual parking, and thus determine whether there is a risk of tire scratches on the vehicle based on the tire movement trajectory, thereby preventing the driver from scratching the tires when parking and avoiding affecting the vehicle's appearance and driving safety.

[0006] Another object of an embodiment of the present invention is to provide a system for preventing tires from being scratched when a vehicle is parked.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides a method for preventing tire scratches when a vehicle is parked, comprising the following steps:

[0009] Obtaining vehicle speed, gear position, and positioning information of a target vehicle, and determining whether the target vehicle is in a parking scene based on the vehicle speed, gear position, and positioning information;

[0010] When the target vehicle is in a parking scene, obtaining environmental image information around the target vehicle, and inputting the environmental image information into a pre-trained stopper detection model to obtain stopper types and stopper positions of a plurality of parking stoppers;

[0011] When the parking space limiter is a sharp side limiter, judging whether there is a risk of tire scratching based on the tire movement trajectory of the target vehicle and the position of the limiter;

[0012] When there is a risk of tire scratches, a warning message is generated to alert the driver.

[0013] Furthermore, in one embodiment of the present invention, determining whether the target vehicle is in a parking scene based on the vehicle speed, the gear position, and the positioning information specifically includes:

[0014] Acquire a plurality of preset historical parking locations, and compare the positioning information with the historical parking locations;

[0015] When the historical parking position is consistent with the positioning information, the vehicle speed is less than or equal to a preset speed threshold, and the gear is a reverse gear, it is determined that the target vehicle is in a parking scene.

[0016] Furthermore, in one embodiment of the present invention, the stopper detection model is trained by the following steps:

[0017] Acquire a plurality of preset parking space sample images, and determine the stopper labels of the parking space sample images through manual annotation, wherein the stopper labels include a stopper type label and a stopper position label;

[0018] Constructing a training data set based on the parking space sample images and the limiter labels;

[0019] Inputting the training data set into a pre-built multi-branch convolutional neural network for training to obtain the trained limiter detection model;

[0020] The limiter type label has sharp sides or smooth sides.

[0021] Furthermore, in one embodiment of the present invention, the multi-branch convolutional neural network includes an input layer, a convolutional layer, a first pooling layer, a first fully connected layer, a second pooling layer, a second fully connected layer, and an output layer. The training data set is input into a pre-built multi-branch convolutional neural network for training to obtain the trained limiter detection model, which specifically includes:

[0022] Inputting the parking space sample image into the convolution layer through the input layer;

[0023] Performing convolution processing on the parking space sample image through the convolution layer to obtain a first feature map;

[0024] Performing pooling processing on the first feature map through the first pooling layer to obtain a second feature map, and performing pooling processing on the first feature map through the second pooling layer to obtain a third feature map;

[0025] Mapping the second feature map to the output layer through the first fully connected layer to obtain a stopper type recognition result, and mapping the third feature map to the output layer through the second fully connected layer to obtain a stopper position recognition result;

[0026] determining a first loss value according to the stopper type identification result and the stopper type label, and determining a second loss value according to the stopper position identification result and the stopper position label;

[0027] The parameters of the multi-branch convolutional neural network are updated through a back propagation algorithm according to the first loss value and the second loss value to obtain the trained limiter detection model.

[0028] Furthermore, in one embodiment of the present invention, when the parking space limiter is a sharp side limiter, determining whether there is a tire scratch risk based on the tire movement trajectory of the target vehicle and the position of the limiter specifically includes:

[0029] When the parking space limiter is a side sharp limiter, the side position of the parking space limiter is determined according to the position of the limiter;

[0030] Obtaining the current body posture, steering angle, and acceleration of the target vehicle;

[0031] Estimate the vehicle body posture change information of the target vehicle in the future period based on the current vehicle body posture, the vehicle speed, the steering angle, and the acceleration

[0032] Determining a left rear tire motion trajectory and a right rear tire motion trajectory according to the left rear tire position and the right rear tire position of the target vehicle and the vehicle body posture change information;

[0033] When the left rear tire motion trajectory passes through the side position, determining that the left rear tire of the target vehicle has a tire scratch risk;

[0034] When the motion trajectory of the right rear tire passes through the side position, it is determined that the right rear tire of the target vehicle has a tire scratch risk.

[0035] Furthermore, in one embodiment of the present invention, when there is a risk of tire scratching, a warning message is generated to alert the driver, which is specifically:

[0036] When there is a risk of tire scratching, corresponding warning prompt information is generated according to the tire position where the risk of tire scratching exists, and the warning prompt information is broadcast.

[0037] Furthermore, in one embodiment of the present invention, when there is a risk of tire scratching, the tire scratch prevention method when the vehicle is parked further includes:

[0038] Determining a real-time distance between a current tire position of the target vehicle and a position of the stopper;

[0039] When the real-time distance is less than or equal to a preset distance threshold, the rear AEB emergency braking system is triggered.

[0040] In a second aspect, an embodiment of the present invention provides a system for preventing tire scratches during parking, comprising:

[0041] a parking scene detection module, configured to obtain vehicle speed, gear position, and positioning information of a target vehicle, and determine whether the target vehicle is in a parking scene based on the vehicle speed, gear position, and positioning information;

[0042] A stopper detection module is used to obtain environmental image information around the target vehicle when the target vehicle is in a parking scene, and input the environmental image information into a pre-trained stopper detection model to obtain the stopper type and stopper position of multiple parking stoppers;

[0043] A tire scratch risk prediction module is used to determine whether there is a tire scratch risk based on the tire movement trajectory of the target vehicle and the position of the stopper when the parking space stopper is a sharp side stopper;

[0044] The warning module is used to generate warning information and alert the driver when there is a risk of tire scratches.

[0045] In a third aspect, an embodiment of the present invention provides a tire scratch prevention device for parking a vehicle, comprising:

[0046] at least one processor;

[0047] at least one memory for storing at least one program;

[0048] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for preventing tire scratches when a vehicle is parked.

[0049] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to execute the above-mentioned method for preventing tire scratches when a vehicle is parked when executed by the processor.

[0050] The advantages and benefits of the present invention will be described in part in the following description and will become apparent from the following description or learned through practice of the present invention:

[0051] The embodiment of the present invention obtains the vehicle speed, gear position and positioning information of the target vehicle, and determines whether the target vehicle is in a parking scene based on the vehicle speed, gear position and positioning information. When the target vehicle is in a parking scene, the environmental image information around the target vehicle is obtained, and the environmental image information is input into a pre-trained limiter detection model to obtain the limiter type and limiter position of several parking limiters. When the parking limiter is a sharp side limiter, it is determined whether there is a risk of tire scratches based on the tire movement trajectory and limiter position of the target vehicle. When there is a risk of tire scratches, an early warning message is generated to alert the driver. The embodiment of the present invention can identify the limiter type and limiter position when the driver performs manual parking, and thus determine whether the vehicle has a risk of tire scratches in combination with the tire movement trajectory, thereby preventing the driver from scratching the tires when parking and avoiding affecting the vehicle's appearance and driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 A flowchart of the steps of a method for preventing tire scratches when parking a vehicle provided by an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of the structure of a multi-branch convolutional neural network provided by an embodiment of the present invention;

[0055] Figure 3 A structural block diagram of a tire scratch prevention system for parking a vehicle provided by an embodiment of the present invention;

[0056] Figure 4 This is a structural block diagram of a tire scratch protection device for parking a vehicle provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0058] In the description of the present invention, "a plurality" means two or more. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly indicating the number of the indicated technical features, or as implicitly indicating the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art.

[0059] Reference Figure 1 The embodiment of the present invention provides a method for preventing tire scratches when a vehicle is parked, which specifically includes the following steps:

[0060] S101, obtaining vehicle speed, gear position, and positioning information of a target vehicle, and determining whether the target vehicle is in a parking scene based on the vehicle speed, gear position, and positioning information;

[0061] S102: When the target vehicle is in a parking scene, obtain environmental image information around the target vehicle, and input the environmental image information into a pre-trained stopper detection model to obtain stopper types and stopper positions of multiple parking stoppers;

[0062] S103: When the parking space limiter is a sharp side limiter, determine whether there is a tire scratch risk based on the tire movement trajectory and the limiter position of the target vehicle;

[0063] S104: When there is a risk of tire scratches, generate a warning message and alert the driver.

[0064] The embodiment of the present invention can identify the limiter type and limiter position when the driver performs manual parking, and thus determine whether the vehicle has a tire scratch risk in combination with the tire movement trajectory, preventing the driver from scratching the tire when parking, and avoiding affecting the vehicle's appearance and driving safety.

[0065] As an optional embodiment, determining whether the target vehicle is in a parking scene based on the vehicle speed, gear position, and positioning information specifically includes:

[0066] S1011. Acquire multiple preset historical parking locations, and compare the positioning information with the historical parking locations;

[0067] S1012: When the historical parking position is consistent with the positioning information, the vehicle speed is less than or equal to the preset speed threshold, and the gear is the reverse gear, it is determined that the target vehicle is in a parking scene.

[0068] Specifically, the speed and gear of the vehicle controlled by the driver and the current GPS position data of the vehicle are obtained, and multiple historical parking positions recorded by the vehicle are obtained. If the current GPS position coincides with the historical parking position, and the current vehicle speed is lower than the speed threshold (such as 5km / h), and the gear is in reverse gear, it is determined that the vehicle is in a parking scene.

[0069] After determining that the vehicle is in a parking scenario, the ADAS parking camera is used to obtain images around the vehicle, which are then input into a pre-trained limiter detection model to obtain the limiter type (sharp side, smooth side) and limiter position of the parking limiters around the vehicle.

[0070] As an optional implementation, the stopper detection model is trained by the following steps:

[0071] S201: Acquire a plurality of preset parking space sample images, and determine the stopper labels of the parking space sample images through manual annotation, where the stopper labels include a stopper type label and a stopper position label;

[0072] S202, constructing a training data set based on parking space sample images and limiter labels;

[0073] S203, inputting the training data set into a pre-built multi-branch convolutional neural network for training to obtain a trained stopper detection model;

[0074] The stopper type label is Sharp Side or Smooth Side.

[0075] Specifically, a plurality of parking space sample images containing different types of parking space limiters are obtained, and the limiter type labels and limiter position labels corresponding to the parking space sample images are determined by manual labeling, wherein the limiter type labels include sharp side edges and smooth side edges, and the limiter position label is the minimum circumscribed rectangular box of the parking space limiter in the parking space sample image; a training data set is constructed based on the parking space sample images and the limiter labels, and the training data set is input into a pre-constructed multi-branch convolutional neural network, and the multi-branch convolutional neural network is used to learn the discrimination of the limiter type and the detection of the limiter position, respectively, to obtain a trained limiter detection model.

[0076] As an optional embodiment, the multi-branch convolutional neural network includes an input layer, a convolution layer, a first pooling layer, a first fully connected layer, a second pooling layer, a second fully connected layer, and an output layer. The training data set is input into the pre-built multi-branch convolutional neural network for training to obtain a trained limiter detection model, which specifically includes:

[0077] S2031. Input the parking space sample image into the convolution layer through the input layer;

[0078] S2032. Perform convolution processing on the parking space sample image through a convolution layer to obtain a first feature map;

[0079] S2033. Performing pooling processing on the first feature map through the first pooling layer to obtain a second feature map, and performing pooling processing on the first feature map through the second pooling layer to obtain a third feature map;

[0080] S2034. Map the second feature map to the output layer through the first fully connected layer to obtain a stopper type recognition result, and map the third feature map to the output layer through the second fully connected layer to obtain a stopper position recognition result;

[0081] S2035: Determine a first loss value based on the stopper type identification result and the stopper type label, and determine a second loss value based on the stopper position identification result and the stopper position label;

[0082] S2036. Update the parameters of the multi-branch convolutional neural network through a back propagation algorithm according to the first loss value and the second loss value to obtain a trained limiter detection model.

[0083] Specifically, if Figure 2The figure shows a schematic diagram of the structure of a multi-branch convolutional neural network provided by an embodiment of the present invention. The parking space sample image is input into the convolution layer through the input layer. The parking space sample image is convolved by the convolution layer to obtain a first feature map. At this time, it is divided into two branches for classifying the type of limiter and detecting the position of the limiter. The first pooling layer of the first branch performs pooling processing on the first feature map to obtain a second feature map. The second feature map is then mapped to the output layer through the first fully connected layer to obtain the limiter type recognition result. The second pooling layer of the second branch performs pooling processing on the first feature map to obtain a third feature map. , the third feature map is mapped to the output layer through the second fully connected layer to obtain the limiter position recognition result; the first loss value is determined according to the limiter type recognition result and the limiter type label, and the second loss value is determined according to the limiter position recognition result and the limiter position label. The overall loss value of the network can be determined according to the first loss value and the second loss value, and then the parameters of the multi-branch convolutional neural network are updated through the back propagation algorithm, and the next round of iterative training is entered. After a preset number of iterations or the loss value reaches a preset threshold or the accuracy on the verification set reaches a preset threshold, a trained limiter detection model can be obtained.

[0084] As a further optional embodiment, when the parking space limiter is a sharp side limiter, determining whether there is a tire scratch risk based on the tire movement trajectory of the target vehicle and the limiter position specifically includes:

[0085] S1031. When the parking limiter is a sharp-side limiter, determine the side position of the parking limiter according to the limiter position;

[0086] S1032: Obtain the current body posture, steering angle, and acceleration of the target vehicle;

[0087] S1033: Estimate the target vehicle's body posture change information in the future based on the current body posture, vehicle speed, steering angle, and acceleration.

[0088] S1034: determining a left rear tire motion trajectory and a right rear tire motion trajectory based on the left rear tire position and the right rear tire position of the target vehicle and the vehicle body posture change information;

[0089] S1035: When the left rear tire's motion trajectory passes through the side position, it is determined that the left rear tire of the target vehicle has a risk of tire scratching;

[0090] S1036: When the movement trajectory of the right rear tire passes the side position, it is determined that the right rear tire of the target vehicle has a risk of tire scratching.

[0091] Specifically, when it is determined that the parking stopper is a sharp-edged side stopper, the specific orientation of the parking stopper can be determined based on the detected stopper position and the captured environmental image information, thereby obtaining the specific position of the side thereof.

[0092] Acquire vehicle motion data in real time, including the current body posture and the status of the steering wheel, accelerator, and brake. Through the built-in vehicle kinematic model, estimate the vehicle's body posture at each future moment and obtain body posture change information.

[0093] Based on the positions of the left rear tire and the right rear tire of the vehicle and the body posture change information, the posture changes of the left rear tire and the right rear tire can be determined, and finally the motion trajectory of the left rear tire and the right rear tire are obtained; when the motion trajectory of the left rear tire passes through the side position, it can be determined that the left rear tire of the target vehicle is at risk of tire scratching, and when the motion trajectory of the right rear tire passes through the side position, it can be determined that the right rear tire of the target vehicle is at risk of tire scratching.

[0094] As a further optional implementation, when there is a risk of tire scratching, a warning message is generated to alert the driver, specifically:

[0095] When there is a risk of tire scratches, a corresponding warning prompt message is generated according to the position of the tire at risk of tire scratches, and the warning prompt message is broadcast.

[0096] Specifically, when there is a risk of tire scratches, a corresponding early warning prompt message is generated according to the orientation of the tire at risk of tire scratches. For example, if there is a risk of tire scratches on the right rear tire, a early warning prompt message "The right rear tire may be scratched, please adjust the reversing route" is generated, and the driver is prompted on the central console through sound and light alarms to avoid tire scratches.

[0097] As a further optional embodiment, when there is a risk of tire scratching, the tire scratch prevention method when the vehicle is parked further includes:

[0098] S105, determining the real-time distance between the current tire position of the target vehicle and the position of the limiter;

[0099] S106: When the real-time distance is less than or equal to a preset distance threshold, trigger the rear AEB emergency braking system.

[0100] Specifically, after determining that there is a risk of tire scratches, the real-time distance between the current tire position of the tire at risk of tire scratches and the detected limiter position (side position) is determined; when the real-time distance is less than or equal to a preset distance threshold (such as 0.5m), the rear AEB emergency braking system is triggered to automatically brake to avoid tire scratches.

[0101] The above describes the method steps of an embodiment of the present invention. It can be appreciated that the embodiment of the present invention can identify the type and position of the stopper when the driver is manually parking, thereby determining whether the vehicle is at risk of tire scratches based on the tire's motion trajectory, thereby preventing the driver from scratching the tires while parking and thus avoiding any impact on the vehicle's appearance and driving safety.

[0102] Reference Figure 3 The embodiment of the present invention provides a system for preventing tire scratches when parking a vehicle, comprising:

[0103] A parking scene detection module is used to obtain the vehicle speed, gear position and positioning information of the target vehicle, and determine whether the target vehicle is in a parking scene based on the vehicle speed, gear position and positioning information;

[0104] The stopper detection module is used to obtain environmental image information around the target vehicle when the target vehicle is in a parking scene, and input the environmental image information into a pre-trained stopper detection model to obtain the stopper type and stopper position of several parking stoppers;

[0105] The tire scratch risk prediction module is used to determine whether there is a tire scratch risk based on the target vehicle's tire movement trajectory and the position of the stopper when the parking space limiter is a sharp side limiter;

[0106] The warning module is used to generate warning information and alert the driver when there is a risk of tire scratches.

[0107] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0108] Reference Figure 4 The embodiment of the present invention provides a tire scratch prevention device for parking a vehicle, comprising:

[0109] at least one processor;

[0110] at least one memory for storing at least one program;

[0111] When the at least one program is executed by the at least one processor, the at least one processor implements the method for preventing tire scratches when a vehicle is parked.

[0112] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0113] An embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor. When the program is executed by the processor, it is used to perform the above-mentioned method for preventing tire scratches when a vehicle is parked.

[0114] A computer-readable storage medium according to an embodiment of the present invention can execute a method for preventing tire scratches during vehicle parking provided by an embodiment of the present invention, can execute any combination of implementation steps of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0115] The embodiment of the present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs Figure 1 The method shown.

[0116] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0117] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present invention set forth in the claims using ordinary skills without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0118] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0119] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0120] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable media on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0121] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0123] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0124] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for preventing tire scratches when a vehicle is parked, characterized in that: The following steps are involved: Obtaining vehicle speed, gear position, and positioning information of a target vehicle, and determining whether the target vehicle is in a parking scene based on the vehicle speed, gear position, and positioning information; When the target vehicle is in a parking scene, obtaining environmental image information around the target vehicle, and inputting the environmental image information into a pre-trained stopper detection model to obtain stopper types and stopper positions of a plurality of parking stoppers; When the parking space limiter is a sharp side limiter, judging whether there is a risk of tire scratching based on the tire movement trajectory of the target vehicle and the position of the limiter; When there is a risk of tire scratches, a warning message is generated to alert the driver.

2. The method for preventing tire scratches when parking a vehicle according to claim 1, characterized in that: The determining whether the target vehicle is in a parking scene according to the vehicle speed, the gear position, and the positioning information specifically includes: Acquire a plurality of preset historical parking locations, and compare the positioning information with the historical parking locations; When the historical parking position is consistent with the positioning information, the vehicle speed is less than or equal to a preset speed threshold, and the gear is a reverse gear, it is determined that the target vehicle is in a parking scene.

3. The method for preventing tire scratches when parking a vehicle according to claim 1, characterized in that: The stopper detection model is trained by the following steps: Acquire a plurality of preset parking space sample images, and determine the stopper labels of the parking space sample images through manual annotation, wherein the stopper labels include a stopper type label and a stopper position label; Constructing a training data set based on the parking space sample images and the limiter labels; Inputting the training data set into a pre-built multi-branch convolutional neural network for training to obtain the trained limiter detection model; The limiter type label has sharp sides or smooth sides.

4. The method for preventing tire scratches when parking a vehicle according to claim 3, characterized in that: The multi-branch convolutional neural network includes an input layer, a convolutional layer, a first pooling layer, a first fully connected layer, a second pooling layer, a second fully connected layer and an output layer. The training data set is input into a pre-built multi-branch convolutional neural network for training to obtain the trained limiter detection model, which specifically includes: Inputting the parking space sample image into the convolution layer through the input layer; Performing convolution processing on the parking space sample image through the convolution layer to obtain a first feature map; Performing pooling processing on the first feature map through the first pooling layer to obtain a second feature map, and performing pooling processing on the first feature map through the second pooling layer to obtain a third feature map; Mapping the second feature map to the output layer through the first fully connected layer to obtain a stopper type recognition result, and mapping the third feature map to the output layer through the second fully connected layer to obtain a stopper position recognition result; determining a first loss value according to the stopper type identification result and the stopper type label, and determining a second loss value according to the stopper position identification result and the stopper position label; The parameters of the multi-branch convolutional neural network are updated through a back propagation algorithm according to the first loss value and the second loss value to obtain the trained limiter detection model.

5. The method for preventing tire scratches when parking a vehicle according to claim 1, characterized in that: When the parking space limiter is a sharp side limiter, judging whether there is a tire scratch risk based on the tire movement trajectory of the target vehicle and the position of the limiter specifically includes: When the parking space limiter is a side sharp limiter, the side position of the parking space limiter is determined according to the position of the limiter; Obtaining the current body posture, steering angle, and acceleration of the target vehicle; Estimate the vehicle body posture change information of the target vehicle in the future period based on the current vehicle body posture, the vehicle speed, the steering angle, and the acceleration Determining a left rear tire motion trajectory and a right rear tire motion trajectory according to the left rear tire position and the right rear tire position of the target vehicle and the vehicle body posture change information; When the left rear tire motion trajectory passes through the side position, determining that the left rear tire of the target vehicle has a tire scratch risk; When the motion trajectory of the right rear tire passes through the side position, it is determined that the right rear tire of the target vehicle has a tire scratch risk.

6. The method for preventing tire scratches when parking a vehicle according to claim 5, characterized in that: When there is a risk of tire scratches, a warning message is generated to alert the driver, specifically: When there is a risk of tire scratching, corresponding warning prompt information is generated according to the tire position where the risk of tire scratching exists, and the warning prompt information is broadcast.

7. A method for preventing tire scratches when parking a vehicle according to any one of claims 1 to 6, characterized in that: When there is a risk of tire scratching, the tire scratch prevention method when the vehicle is parked further includes: Determining a real-time distance between a current tire position of the target vehicle and a position of the stopper; When the real-time distance is less than or equal to a preset distance threshold, the rear AEB emergency braking system is triggered.

8. A tire scratch prevention system for a vehicle when parking, characterized in that: include: a parking scene detection module, configured to obtain vehicle speed, gear position, and positioning information of a target vehicle, and determine whether the target vehicle is in a parking scene based on the vehicle speed, gear position, and positioning information; A stopper detection module is used to obtain environmental image information around the target vehicle when the target vehicle is in a parking scene, and input the environmental image information into a pre-trained stopper detection model to obtain the stopper type and stopper position of multiple parking stoppers; A tire scratch risk prediction module is used to determine whether there is a tire scratch risk based on the tire movement trajectory of the target vehicle and the position of the stopper when the parking space stopper is a sharp side stopper; The warning module is used to generate warning information and alert the driver when there is a risk of tire scratches.

9. A tire scratch prevention device for a vehicle when parking, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method for preventing tire scratches during vehicle parking according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to execute the method for preventing tire scratches when a vehicle is parked as claimed in any one of claims 1 to 7 when the program is executed by the processor.

Images