Vision-based road surface peak adhesion coefficient detection method and device

Abstract

The invention discloses a vision-based road surface peak adhesion coefficient detection method and device. The method comprises the following steps: acquiring a sensor signal of a vehicle and an image in front of the vehicle; performing image conversion on the image in front of the vehicle to obtain a corresponding aerial view; in the aerial view, based on a sensor signal, determining a region of interest for road surface peak adhesion coefficient estimation through vehicle kinematics; and estimating a road surface peak adhesion coefficient based on the region of interest and the aerial view to obtain an estimation result of the road surface peak adhesion coefficient. According to the method, the front view in the foresight view angle is converted into the aerial view in the overlook view angle, the influence of a large number of background factors on image detection is eliminated, the region of interest for estimating the road surface peak adhesion coefficient is determined through vehicle kinematics, the accuracy and real-time performance of the road surface peak adhesion coefficient are improved, and computing resources are saved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method and device for detecting a peak adhesion coefficient of a road surface based on vision. Background Art

[0002] Road adhesion conditions are directly related to vehicle driving safety. The peak road adhesion coefficient can quantify the maximum interaction strength between tires and roads, and plays a decisive role in the acceleration, braking and handling stability of the car. It is one of the core parameters. Based on this, it is necessary to accurately estimate the peak road adhesion coefficient in real time, so as to significantly broaden the working range of the car's active safety system and make it more flexible to respond to various road conditions.

[0003] In the prior art, the peak adhesion coefficient of the road surface can be detected based on the front view, but the background of the front view may affect the road surface detection. For example, the background such as the sky may be misidentified as a certain road surface during the process of determining the road surface type, thereby reducing the accuracy of the peak adhesion coefficient of the road surface. In addition, the traditional method uses semantic segmentation to detect the drivable area and estimate the entire road surface in front of the vehicle, which consumes a lot of computing resources. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] To this end, one purpose of the present invention is to propose a vision-based road peak adhesion coefficient detection method, which converts the front view from a forward perspective into a bird's-eye view from a top-down perspective, eliminating the influence of a large number of background factors on image detection, and uses vehicle kinematics to determine the area of ​​interest for road peak adhesion coefficient estimation, thereby improving the accuracy and real-time performance of the road peak adhesion coefficient and saving computing resources.

[0006] Another object of the present invention is to provide a vision-based road surface peak adhesion coefficient detection device.

[0007] To achieve the above object, an embodiment of the present invention provides a method for detecting a peak adhesion coefficient of a road surface based on vision, comprising:

[0008] Acquire sensor signals of the vehicle and images in front of the vehicle;

[0009] Performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view;

[0010] In the bird's-eye view, determining an area of ​​interest for estimating a peak road adhesion coefficient through vehicle kinematics based on the sensor signal;

[0011] The peak adhesion coefficient of the road surface is estimated based on the region of interest and the bird's-eye view to obtain an estimation result of the peak adhesion coefficient of the road surface.

[0012] The visual-based road surface peak adhesion coefficient detection method of the embodiment of the present invention may also have the following additional technical features:

[0013] Furthermore, performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view includes: performing image conversion on the image in front of the vehicle based on an inverse perspective transformation to obtain a corresponding bird's-eye view.

[0014] Further, the sensor signal includes a current vehicle speed and a front wheel steering angle; and the region of interest for estimating a peak road adhesion coefficient based on the sensor signal and determined by vehicle kinematics includes:

[0015] determining a current position of the vehicle;

[0016] Based on the current position of the vehicle, the current vehicle speed and the front wheel steering angle, a predicted trajectory of the vehicle is obtained through a vehicle kinematic equation;

[0017] Based on the predicted trajectory and the preset width, a region of interest for estimating a peak road adhesion coefficient is determined.

[0018] Further, the estimating the peak adhesion coefficient of the road surface based on the region of interest and the image to obtain an estimation result of the peak adhesion coefficient of the road surface includes:

[0019] Detecting the road surface in the area of ​​interest in the bird's-eye view through a target deep learning network model to obtain a classification result of the road surface type;

[0020] Based on the classification result of the road surface type, an estimation result of a road surface peak adhesion coefficient is determined.

[0021] Furthermore, before detecting the road surface in the region of interest in the bird's-eye view by using the target deep learning network model to obtain a classification result of the road surface type, the method further includes:

[0022] Acquire first training data, and filter the first training data to obtain second training data;

[0023] Labeling the second training data to obtain third training data;

[0024] Based on the third training data, obtain a corresponding training data set and a verification data set;

[0025] Training the initial deep learning network model based on the training data set to obtain a trained deep learning network model;

[0026] The trained deep learning network model is verified using the verification data set to obtain a target deep learning network model.

[0027] Furthermore, the determining of the estimation result of the peak adhesion coefficient of the road surface based on the classification result of the road surface type includes:

[0028] Determine the mapping relationship between road surface type and road surface peak adhesion coefficient;

[0029] Based on the classification result of the road surface type, an estimation result of the road surface peak adhesion coefficient is determined through the mapping relationship.

[0030] To achieve the above object, another embodiment of the present invention provides a device for detecting peak road adhesion coefficient based on vision, the device comprising:

[0031] An acquisition module, used for acquiring a sensor signal of the vehicle and an image in front of the vehicle;

[0032] An image conversion module, used for performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view;

[0033] A determination module, configured to determine, in the bird's-eye view, an area of ​​interest for estimating a peak road adhesion coefficient through vehicle kinematics based on the sensor signal;

[0034] The estimation module is used to estimate the peak adhesion coefficient of the road surface based on the region of interest and the bird's-eye view to obtain an estimation result of the peak adhesion coefficient of the road surface.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0037] Figure 1 A flow chart of a method for detecting a peak adhesion coefficient of a road surface based on vision according to an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of a vehicle kinematics model according to an embodiment of the present invention;

[0039] Figure 3 The figure is a schematic diagram of the structure of a device for detecting peak adhesion coefficient of a road surface based on vision according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] Embodiments of the present invention are described in detail below, examples of which 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 intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0041] The following describes a method and device for detecting a peak adhesion coefficient of a road surface based on vision according to an embodiment of the present invention with reference to the accompanying drawings.

[0042] First, a method for detecting a peak adhesion coefficient of a road surface based on vision according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0043] Figure 1 The figure is a flow chart of a method for detecting peak adhesion coefficient of a road surface based on vision according to an embodiment of the present invention.

[0044] like Figure 1 As shown, the vision-based road peak adhesion coefficient detection method includes the following steps:

[0045] Step S1, acquiring a sensor signal of the vehicle and an image in front of the vehicle;

[0046] Wherein, in one embodiment of the present invention, the sensor signal may include the current vehicle speed and the front wheel turning angle. In one embodiment of the present invention, the sensor signal of the vehicle may be acquired through a sensor.

[0047] Furthermore, in one embodiment of the present invention, an onboard camera can be used to capture images in front of the vehicle, with an image resolution of 1920×1080 and a capture frequency of 30 frames per second. The onboard camera is arranged below the rearview mirror on the inside of the front windshield, and the camera viewing angle is adjusted so that the bottom of the field of view is located at the edge of the hood, and the road surface in the captured image occupies more than three-fifths of the entire screen, ensuring that the road surface area in the captured image exceeds 50 meters.

[0048] Furthermore, in one embodiment of the present invention, the inertial navigation system can be used to collect clock source signals through the GPRMC protocol, with an acquisition frequency of 100 Hz. The entire system uses the clock source signal as a time reference to record time stamps.

[0049] In one embodiment of the present invention, the image of the above-mentioned vehicle can be transmitted to the on-board industrial computer via USB, the vehicle speed and front wheel angle signals can be transmitted to the industrial computer via the CAN interface, the inertial navigation system transmits signals to the industrial computer via the serial port, and the industrial computer uses the UTC time collected by the inertial navigation system to timestamp the image, point cloud, vehicle speed and front wheel angle records, providing a reference basis for subsequent time and space synchronization.

[0050] Step S2, performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view;

[0051] In one embodiment of the present invention, after the image in front of the vehicle is obtained through the above steps, the image in front of the vehicle can be converted to obtain a corresponding bird's-eye view.

[0052] Specifically, in one embodiment of the present invention, the method of performing image conversion on the image in front of the vehicle to obtain the corresponding bird's-eye view may include: performing image conversion on the image in front of the vehicle based on inverse perspective transformation to obtain the corresponding bird's-eye view.

[0053] In one embodiment of the present invention, the image in front of the vehicle can be transformed by the inverse perspective transformation of the first formula to obtain the corresponding bird's-eye view, wherein the first formula is:

[0054]

[0055] Among them, θ represents the vehicle pitch angle, (U, V) represents the camera coordinate system, (M, N) represents the image width and height, x0(r, c) and y0(r, c) represent the horizontal and vertical coordinates mapped from the image coordinate system to the world coordinate system, and C = (C x ,C y ,C z ) represents the position of the camera in world coordinates,

[0056] in, AlphaV and AlphaU represent the aperture angle of the camera in the vertical and horizontal directions. Among them, F is the focal length of the camera, and H and W are the height and width of the photosensitive element.

[0057] Furthermore, in one embodiment of the present invention, when a vehicle is driving, in many cases the driving direction of the vehicle is not parallel to the road direction, and a yaw angle is required to compensate and eliminate this phenomenon. Based on this, the second formula can be used for compensation to make the main road direction in the inverse perspective transformation result more parallel to the V axis in the image coordinate system, wherein the second formula is:

[0058]

[0059] Among them, x c (r,c) and y c (r, c) is the coordinate after compensation, and ψ represents the vehicle yaw angle.

[0060] And, in one embodiment of the present invention, a corresponding bird's-eye view can be obtained based on the corrected coordinates obtained through the above steps.

[0061] Step S3, in the bird's-eye view, based on the sensor signal, determine the area of ​​interest for estimating the peak adhesion coefficient of the road surface through vehicle kinematics;

[0062] In one embodiment of the present invention, after obtaining the bird's-eye view through the above steps, the region of interest for estimating the peak adhesion coefficient of the road surface can be determined in the bird's-eye view based on the sensor signal and vehicle kinematics.

[0063] Specifically, in one embodiment of the present invention, a method for determining an area of ​​interest for estimating a peak road adhesion coefficient through vehicle kinematics based on a sensor signal may include the following steps:

[0064] Step S31, determining the current position of the vehicle;

[0065] Step S32, based on the current position, current speed and front wheel steering angle of the vehicle, obtain the predicted trajectory of the vehicle through the vehicle kinematic equation;

[0066] Step S33, determining an area of ​​interest for estimating the peak adhesion coefficient of the road surface based on the predicted trajectory and the preset width.

[0067] Among them, in one embodiment of the present invention, Figure 2 FIG. 1 is a schematic diagram of a vehicle kinematic model proposed in an embodiment of the present invention. Figure 2 As shown, the vehicle kinematic equation is:

[0068]

[0069] Among them, (x, y) is the position of the vehicle's center of mass in the world coordinate system, v is the vehicle speed, δ f is the front wheel turning angle, a and b are the distances from the center of mass to the front axle and rear axle respectively.

[0070] And, the position of the left front wheel (x fL ,y fL ) and the right front wheel position (x fR ,y fR ) can be expressed as:

[0071]

[0072] Among them, B is the front wheelbase.

[0073] In one embodiment of the present invention, with the current position as a reference, the current vehicle speed and the front wheel steering angle as fixed inputs, the trajectories of the left front wheel and the right front wheel are predicted through the above steps to obtain the predicted trajectory of the vehicle, wherein the predicted distance is set to 10m, and when the vehicle speed is less than 5km / h, the vehicle speed is taken as 5km / h.

[0074] In one embodiment of the present invention, the predicted trajectories of the left and right front wheels are used as the center line, and the preset width is twice the width of the front wheel tire, which is determined as the area of ​​interest for estimating the road adhesion coefficient.

[0075] In one embodiment of the present invention, the above-mentioned determination of the corresponding region of interest based on vehicle kinematics, that is, the adhesion coefficient is only a description of the relationship between the tire and the ground, and only the road surface on the vehicle's driving trajectory needs to be estimated, saving computing resources.

[0076] Step S4, estimating the peak adhesion coefficient of the road surface based on the region of interest and the bird's-eye view, and obtaining an estimation result of the peak adhesion coefficient of the road surface.

[0077] In one embodiment of the present invention, after the region of interest and the bird's-eye view are determined through the above steps, the peak adhesion coefficient of the road surface can be estimated based on the region of interest and the bird's-eye view to obtain an estimation result of the peak adhesion coefficient of the road surface.

[0078] Specifically, in one embodiment of the present invention, the method for estimating the peak adhesion coefficient of the road surface based on the region of interest and the bird's-eye view to obtain the estimation result of the peak adhesion coefficient of the road surface may include the following steps:

[0079] Step S41, detecting the road surface in the area of ​​interest in the bird's-eye view through the target deep learning network model to obtain a classification result of the road surface type;

[0080] Step S42: determining an estimation result of a peak road adhesion coefficient based on the classification result of the road type.

[0081] Furthermore, in one embodiment of the present invention, before detecting the road surface in the region of interest in the bird's-eye view through the target deep learning network model to obtain the classification result of the road surface type, the method may further include the following steps:

[0082] Step 1: Obtain first training data, and filter the first training data to obtain second training data;

[0083] Step 2: label the second training data to obtain third training data;

[0084] Step 3: Based on the third training data, obtain a corresponding training data set and a verification data set;

[0085] Step 4: Train the initial deep learning network model based on the training data set to obtain a trained deep learning network model;

[0086] Step 5: Use the verification data set to verify the trained deep learning network model to obtain the target deep learning network model.

[0087] In one embodiment of the present invention, the collected road images under various weather conditions are used as the first training data, and the images in the first training data are screened for clarity, and blurred images are removed to obtain the second training data.

[0088] Furthermore, in one embodiment of the present invention, the labelImg image annotation software can be used to label the images in the second training data, and the positions and types of road features in the images are annotated to obtain the third training data, wherein the road types are divided into eight categories, namely dry asphalt road surface, wet asphalt road surface, dry cement road surface, wet cement road surface, brick paved road surface, loose snow road surface, compacted snow road surface, and ice film road surface.

[0089] In one embodiment of the present invention, the third training data can be divided into a training data set and a verification data set for training the initial deep learning network model according to a preset ratio. For example, assuming that the preset ratio is 7:3, that is, 70% of the data in the third training data is randomly divided into a training data set and 30% of the data is divided into a verification data set.

[0090] Further, in one embodiment of the present invention, the method of training the initial deep learning network model based on the training data set to obtain a trained deep learning network model may include the following steps:

[0091] Step a: input the data in the training data set into the initial deep learning network model in batches to obtain the classification results of the predicted road surface type;

[0092] Step b, inputting the classification result of the predicted road surface type and the classification result of the actual road surface type into the loss function to obtain the corresponding loss value;

[0093] Step c: Use the loss value to update the network parameters in the initial deep learning network model until the number of iterations of the network parameters reaches a preset number, thereby obtaining a trained deep learning network model.

[0094] In one embodiment of the present invention, the deep learning network model may be YOLOv10-S.

[0095] And, in one embodiment of the present invention, the images in the training set can be n A batch of 10 ...

[0096] Furthermore, in one embodiment of the present invention, the above loss function is the same as that in the prior art, and the embodiment of the present disclosure will not be described in detail here.

[0097] Furthermore, in one embodiment of the present invention, after the trained deep learning network model is obtained through the above steps, the trained deep learning network model can be verified using a verification data set. If the road feature recognition accuracy of each image in the verification data set is greater than 90%, the trained deep learning network model is determined as the target deep learning network model; otherwise, it is necessary to continue training the model based on the previous training, and repeat this process until the accuracy requirement is met.

[0098] Furthermore, in one embodiment of the present invention, after obtaining the target deep learning network model through the above steps, the target deep learning network model can be used to detect the road surface in the area of ​​interest in the bird's-eye view to obtain a classification result of the road surface type.

[0099] Furthermore, in one embodiment of the present invention, after obtaining the classification result of the road surface type through the above steps, the method for determining the estimation result of the road surface peak adhesion coefficient based on the classification result of the road surface type may include the following steps:

[0100] Step 1: determine the mapping relationship between road surface type and road surface peak adhesion coefficient;

[0101] Step 2: Based on the classification result of the road surface type, the estimation result of the road surface peak adhesion coefficient is determined through the mapping relationship.

[0102] Among them, in one embodiment of the present invention, after obtaining the classification results of the road surface types through the above steps, it is considered that the road surface adhesion coefficient is related to influencing factors such as road surface wear, tire wear, and air temperature and humidity, and the road surface adhesion coefficient range value at different driving speeds is also different. Based on this, the road surface adhesion coefficient range of each road surface type at different vehicle speeds is determined with reference to the existing published "GA / T643-2006 Technical Appraisal of Vehicle Driving Speed ​​in Typical Traffic Accident Forms", and the peak road surface adhesion coefficient is selected as the most. Among them, Table 1 is a mapping relationship comparison table between a road surface type and a road surface peak adhesion coefficient proposed in an embodiment of the present invention.

[0103] Table 1

[0104]

[0105] Furthermore, in one embodiment of the present invention, the mapping relationship between the road surface type and the road surface peak adhesion coefficient is determined through the above steps, and the estimation result of the road surface peak adhesion coefficient can be determined through the mapping relationship based on the classification result of the road surface type.

[0106] In one embodiment of the present invention, the estimated result of the road adhesion coefficient can be obtained by querying the corresponding relationship in Table 1 according to the classification result of the road type, and the estimated result is in the form of a vector [index c ,conf c ,e c ,v,UTC], where index c For road surface type, conf c represents the confidence level, e c represents the peak road adhesion coefficient, v represents the vehicle speed, and UTC represents the timestamp.

[0107] According to the vision-based road peak adhesion coefficient detection method proposed in an embodiment of the present invention, the front view under the front view perspective is converted into a bird's-eye view under the top view perspective, eliminating the influence of a large number of background factors on image detection, and using vehicle kinematics to determine the area of ​​interest for road peak adhesion coefficient estimation, thereby improving the accuracy and real-time performance of the road peak adhesion coefficient and saving computing resources.

[0108] Next, a vision-based road surface peak adhesion coefficient detection device according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0109] Figure 3 The figure is a schematic diagram of the structure of a device for detecting peak adhesion coefficient of a road surface based on vision according to an embodiment of the present invention.

[0110] like Figure 3 As shown, the vision-based road peak adhesion coefficient detection device 10 includes: an acquisition module 301 , an image conversion module 302 , a determination module 303 and an estimation module 304 .

[0111] An acquisition module 301 is used to acquire a sensor signal of the vehicle and an image in front of the vehicle;

[0112] An image conversion module 302 is used to convert the image in front of the vehicle to obtain a corresponding bird's-eye view;

[0113] A determination module 303 is used to determine an area of ​​interest for estimating a peak road adhesion coefficient through vehicle kinematics based on the sensor signal in the bird's-eye view;

[0114] The estimation module 304 is used to estimate the peak adhesion coefficient of the road surface based on the region of interest and the bird's-eye view to obtain an estimation result of the peak adhesion coefficient of the road surface.

[0115] Furthermore, the image conversion module 302 is specifically used for:

[0116] The image in front of the vehicle is transformed based on the inverse perspective transformation to obtain the corresponding bird's-eye view.

[0117] Furthermore, the sensor signal includes the current vehicle speed and the front wheel steering angle; the determination module 303 is specifically used for:

[0118] Determine the current location of the vehicle;

[0119] Based on the vehicle's current position, current speed and front wheel angle, the vehicle's predicted trajectory is obtained through the vehicle's kinematic equations;

[0120] Based on the predicted trajectory and the preset width, the region of interest for estimating the peak road adhesion coefficient is determined.

[0121] Furthermore, the estimation module 304 is specifically used for:

[0122] The target deep learning network model is used to detect the road surface in the area of ​​interest in the bird's-eye view and obtain the classification result of the road surface type;

[0123] Based on the classification result of the road surface type, an estimation result of the peak road surface adhesion coefficient is determined.

[0124] Furthermore, the above device is also used for:

[0125] Acquire first training data, and filter the first training data to obtain second training data;

[0126] Labeling the second training data to obtain third training data;

[0127] Based on the third training data, a corresponding training data set and a verification data set are obtained;

[0128] The initial deep learning network model is trained based on the training data set to obtain a trained deep learning network model;

[0129] The validation data set is used to validate the trained deep learning network model to obtain the target deep learning network model.

[0130] Furthermore, the above device is also used for:

[0131] Determine the mapping relationship between road surface type and road surface peak adhesion coefficient;

[0132] Based on the classification results of the road surface type, the estimation result of the road surface peak adhesion coefficient is determined through the mapping relationship.

[0133] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and will not be repeated here.

[0134] According to the vision-based road peak adhesion coefficient detection device proposed in an embodiment of the present invention, the front view under the front view perspective is converted into a bird's-eye view under the top view perspective, eliminating the influence of a large number of background factors on image detection, and using vehicle kinematics to determine the area of ​​interest for road peak adhesion coefficient estimation, thereby improving the accuracy and real-time performance of the road peak adhesion coefficient and saving computing resources.

[0135] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0136] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. 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 representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0137] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for detecting peak road adhesion coefficient based on vision, characterized in that: The method comprises: Acquire sensor signals of the vehicle and images in front of the vehicle; Performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view; In the bird's-eye view, determining an area of ​​interest for estimating peak road surface adhesion coefficients through vehicle kinematics based on the sensor signals; The peak adhesion coefficient of the road surface is estimated based on the region of interest and the bird's-eye view to obtain an estimation result of the peak adhesion coefficient of the road surface.

2. The method according to claim 1, characterized in that Performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view includes: performing image conversion on the image in front of the vehicle based on inverse perspective transformation to obtain a corresponding bird's-eye view.

3. The method according to claim 1, characterized in that The sensor signal includes the current vehicle speed and the front wheel steering angle; the region of interest for estimating the peak road adhesion coefficient based on the sensor signal and determined by vehicle kinematics includes: determining a current position of the vehicle; Based on the current position of the vehicle, the current vehicle speed and the front wheel steering angle, a predicted trajectory of the vehicle is obtained through a vehicle kinematic equation; Based on the predicted trajectory and the preset width, a region of interest for estimating a peak road adhesion coefficient is determined.

4. The method according to claim 1, characterized in that: The estimating the peak adhesion coefficient of the road surface based on the region of interest and the image to obtain an estimation result of the peak adhesion coefficient of the road surface includes: Detecting the road surface in the area of ​​interest in the bird's-eye view through a target deep learning network model to obtain a classification result of the road surface type; Based on the classification result of the road surface type, an estimation result of a road surface peak adhesion coefficient is determined.

5. The method according to claim 4, characterized in that Before detecting the road surface in the region of interest in the bird's-eye view by using the target deep learning network model to obtain a classification result of the road surface type, the method further includes: Acquire first training data, and filter the first training data to obtain second training data; Labeling the second training data to obtain third training data; Based on the third training data, obtain a corresponding training data set and a verification data set; Training the initial deep learning network model based on the training data set to obtain a trained deep learning network model; The trained deep learning network model is verified using the verification data set to obtain a target deep learning network model.

6. The method according to claim 4, characterized in that The step of determining an estimation result of a peak road adhesion coefficient based on the classification result of the road surface type includes: Determine the mapping relationship between road surface type and road surface peak adhesion coefficient; Based on the classification result of the road surface type, an estimation result of the road surface peak adhesion coefficient is determined through the mapping relationship.

7. A visual-based road peak adhesion coefficient detection device, characterized in that: The device comprises: An acquisition module, used for acquiring a sensor signal of the vehicle and an image in front of the vehicle; An image conversion module, used for performing image conversion on the image in front of the vehicle to obtain a corresponding bird's-eye view; A determination module, configured to determine, in the bird's-eye view, an area of ​​interest for estimating a peak road adhesion coefficient through vehicle kinematics based on the sensor signal; The estimation module is used to estimate the peak adhesion coefficient of the road surface based on the region of interest and the bird's-eye view to obtain an estimation result of the peak adhesion coefficient of the road surface.

8. The device according to claim 7, characterized in that The image conversion module is specifically used for: The image in front of the vehicle is transformed based on inverse perspective transformation to obtain a corresponding bird's-eye view.

9. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images