Road surface recognition method and system, computer readable storage medium, electronic equipment and vehicle

Abstract

The invention discloses a road surface recognition method and system, a computer readable storage medium, electronic equipment and a vehicle, and the method comprises the steps: obtaining one or more images of a current road surface through a vehicle-mounted visual device, and obtaining the type of the current road surface based on the one or more images of the current road surface; obtaining a first road adhesion coefficient of the current road according to vehicle dynamics; when the road surface type is not included in the road surface type-road surface adhesion coefficient mapping table, obtaining a second road surface adhesion coefficient of the current road surface based on the one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface; and obtaining a third pavement adhesion coefficient based on the first pavement adhesion coefficient and the second pavement adhesion coefficient.

Description

Technical Field

[0001] The present invention relates to the technical field of road surface recognition, and in particular to a road surface recognition method, system, computer-readable storage medium, electronic equipment and vehicle. Background Art

[0002] Existing road surface recognition methods, such as vision-based road surface type recognition methods, use image processing and other technical means to classify frames of the video stream from the vehicle-mounted camera and then obtain the road surface adhesion coefficient by looking up a table. This method has good predictive ability, but the recognition result is generally a range value of the road surface adhesion coefficient, which has a certain degree of recognition error, and cannot be obtained for roads outside the existing road surface-adhesion coefficient mapping table. Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] The present invention provides a road surface recognition method, comprising:

[0005] Acquire one or more images of the current road surface through a vehicle-mounted visual device, and obtain a road surface type of the current road surface based on the one or more images of the current road surface;

[0006] Obtaining a first road adhesion coefficient of the current road surface according to vehicle dynamics;

[0007] When the road surface type is not included in the road surface type-road surface adhesion coefficient mapping table, obtaining a second road surface adhesion coefficient of the current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface;

[0008] A third road surface adhesion coefficient is obtained based on the first road surface adhesion coefficient and the second road surface adhesion coefficient.

[0009] Exemplarily, obtaining a second road surface adhesion coefficient of the current road surface based on one or more images of the current road surface and a first road surface adhesion coefficient of the current road surface includes:

[0010] One or more images of the current road surface and the first road surface adhesion coefficient of the current road surface are input into a deep learning model to obtain an output second road surface adhesion coefficient of the current road surface.

[0011] Exemplarily, obtaining the road surface type of the current road surface based on the one or more images of the current road surface includes:

[0012] Segmenting the one or more images of the current road surface one by one to extract road surface portions from the one or more images;

[0013] The road surface portion in the one or more images is input into a classifier to obtain an output road surface type of the current road surface.

[0014] Exemplarily, the road surface identification method further includes: updating the road surface type of the current road surface and the second road surface adhesion coefficient of the current road surface online into the road surface type-road surface adhesion coefficient mapping table to obtain an online updated road surface type-road surface adhesion coefficient mapping table.

[0015] Exemplarily, obtaining a first road adhesion coefficient of a current road surface according to vehicle dynamics includes:

[0016] Based on the ABS point brake slip rate control, the braking force limited slip rate is obtained;

[0017] Obtaining a driving force limited slip control slip ratio based on the motor driving torque limited slip control;

[0018] The first road surface adhesion coefficient is obtained based on the braking force limited slip slip ratio and the driving force limited slip control slip ratio.

[0019] Exemplarily, each frame of image and the first road adhesion coefficient at the same time constitute a data pair.

[0020] Exemplarily, the road surface type-road surface adhesion coefficient mapping table includes a plurality of data pairs in which the road surface type and the second road surface adhesion coefficient correspond one to one.

[0021] The present invention also provides a road surface recognition system, comprising:

[0022] A road surface acquisition module, used to acquire one or more images of the current road surface through a vehicle-mounted visual device, and obtain a road surface type of the current road surface based on the one or more images of the current road surface;

[0023] A first road surface adhesion coefficient acquisition module, used for obtaining a first road surface adhesion coefficient of a current road surface according to vehicle dynamics;

[0024] A second road surface adhesion coefficient acquisition module, configured to obtain a second road surface adhesion coefficient of a current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface when the road surface type is not included in a road surface type-road surface adhesion coefficient mapping table;

[0025] The third road surface adhesion coefficient acquisition module is used to obtain a third road surface adhesion coefficient based on the first road surface adhesion coefficient and the second road surface adhesion coefficient.

[0026] The present invention also provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the road surface recognition method described in any one of claims 1-7.

[0027] The present invention also provides an electronic device, comprising a processor and a memory, wherein the processor is used in any of the above road surface recognition methods.

[0028] The present invention also provides a vehicle, comprising the electronic device mentioned above.

[0029] According to the road surface recognition method, system, computer-readable storage medium, electronic device and vehicle provided by the present invention, when the road surface type of the current road surface is not included in the existing road surface type-road surface adhesion coefficient mapping table, the second road surface adhesion coefficient of the current road surface is obtained based on one or more images of the current road surface obtained by the on-board visual device and the first road surface adhesion coefficient of the current road surface obtained according to vehicle dynamics, and the road surface type of the current road surface and the second road surface adhesion coefficient of the current road surface are updated online to the existing road surface type-road surface adhesion coefficient mapping table to obtain an online updated road surface type-road surface adhesion coefficient mapping table, and further obtain the third road surface adhesion coefficient based on both the first road surface adhesion coefficient and the second road surface adhesion coefficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The following drawings of the present invention are used to understand the present invention as part of the present invention. The embodiments of the present invention are shown in the drawings and the description thereof is used to explain the principle of the present invention.

[0031] In the attached figure:

[0032] Figure 1 is a schematic structural diagram of a vehicle according to an embodiment of the present invention;

[0033] Figure 2 is a flow chart of a road surface recognition method according to an embodiment of the present invention;

[0034] Figure 3 The flowchart is a flowchart of obtaining a first road surface adhesion coefficient of a current road surface according to vehicle dynamics according to an embodiment of the present invention.

[0035] Figure 4 Schematic diagram of a road surface type-road surface adhesion coefficient mapping table according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0037] It should be understood that the present invention can be implemented in different forms and should not be construed as being limited to the embodiments presented herein. On the contrary, providing these embodiments will make the disclosure thorough and complete and fully convey the scope of the present invention to those skilled in the art. In the accompanying drawings, the sizes and relative sizes of layers and regions may be exaggerated for clarity. The same reference numerals throughout represent the same elements.

[0038] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present invention. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0039] In order to fully understand the present invention, detailed steps and detailed structures will be presented in the following description to illustrate the technical solution proposed by the present invention. The preferred embodiments of the present invention are described in detail below, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0040] In order to solve the problem that a road surface type-road surface adhesion coefficient mapping table cannot be updated online, the present invention provides a road surface recognition method, system, computer-readable storage medium, electronic device and vehicle.

[0041] First refer to Figure 1 A schematic structural diagram of a vehicle 100 is described.

[0042] like Figure 1 As shown, the vehicle 100 includes a vehicle-mounted visual device 110 , a vehicle sensor device 120 , and an electronic device 130 .

[0043] In one embodiment, the vehicle-mounted visual device 110 is used to collect one or more images of the current road surface. Specifically, the vehicle-mounted visual device 110 includes a camera. The types of cameras include but are not limited to long-range cameras, mid-range cameras, stereo cameras, wide-angle cameras (e.g., fisheye cameras), surround cameras (e.g., 360-degree cameras), infrared cameras, or combinations thereof. In one embodiment, video information of the current road surface is collected by a camera installed on the vehicle.

[0044] In one embodiment, the vehicle sensing device 120 is used to collect sensor signals of the vehicle. The vehicle sensing device 120 includes one or more sensors, such as a speed sensor, a pressure sensor, a temperature sensor, an ABS sensor, a camshaft position sensor, a crankshaft position sensor, etc. In one embodiment, sensor signals are received by one or more sensors of the vehicle, such as wheel speed signals, brake pedal signals, throttle signals, EPS angle signals, IMU signals, vehicle speed estimation signals, motor torque signals, etc.

[0045] In one embodiment, the electronic device 130 includes a processor 131 and a memory 132. The processor 131 can be implemented as software, hardware, firmware or any combination thereof, and can use a single or multiple application specific integrated circuits (ASIC), a single or multiple general purpose integrated circuits, a single or multiple microprocessors, a single or multiple programmable logic devices, or any combination of the aforementioned circuits and / or devices, or other suitable circuits or devices. In addition, the processor 131 can control other components in the vehicle 100 to perform the corresponding steps of the method described below. The memory 132 can be a flash memory card, a solid-state memory, a hard disk, etc. It can be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0046] It should be understood that Figure 1 The components included in the vehicle 100 are only exemplary, and the vehicle 100 may include more or fewer components, and the present invention is not limited thereto.

[0047] The present invention also provides a road surface recognition method 200, such as Figure 2 As shown, including:

[0048] Step S210: acquiring one or more images of the current road surface through a vehicle-mounted visual device, and obtaining a road surface type of the current road surface based on the one or more images of the current road surface;

[0049] Step S220: obtaining a first road adhesion coefficient of the current road surface according to vehicle dynamics;

[0050] Step S230: when the road type is not included in the road type-road adhesion coefficient mapping table, obtaining a second road adhesion coefficient of the current road based on one or more images of the current road and the first road adhesion coefficient of the current road;

[0051] Step S240: Obtaining a third road surface adhesion coefficient based on the first road surface adhesion coefficient and the second road surface adhesion coefficient.

[0052] In step S210, one or more images of the current road surface can be obtained through the on-board visual device arranged on the vehicle, and the one or more images can exist in the form of static images or dynamic videos. The collected images can be used for classifier training, and the training data of the classifier needs to collect pictures under various road conditions, including road scenes of structured and unstructured roads under various weather and lighting conditions. In the road condition picture collection stage, it is mainly to ensure that the road type, lighting and weather conditions, and road structure contained in the data are as diverse as possible, wherein the road types include but are not limited to dry asphalt, wet asphalt, wet concrete road surface, cobblestone road surface, muddy and slippery road surface, ice road surface, snow road surface, etc.; weather conditions include but are not limited to clear weather, weather just after rain, heavy rain, snowy day, etc.; lighting conditions include dawn, morning, noon, dusk, night, etc.

[0053] Exemplarily, obtaining the road surface type of the current road surface based on one or more images of the current road surface includes: segmenting the one or more images of the current road surface one by one to extract the road surface portion in the one or more images; inputting the road surface portion in the one or more images into a classifier to obtain the output road surface type of the current road surface. The classifier includes a decision tree, a random forest, a deep convolutional neural network, a combination of a deep convolutional neural network and a recursive neural network and variants thereof, or a combination of a deep convolutional neural network and a conditional random field.

[0054] In one embodiment, for the video stream obtained from the vehicle-mounted visual device, the frame extraction process is first performed to obtain a picture library; then the image and processing module uses the pre-trained CNN to segment the pictures one by one and extract the road surface part of interest; then the pre-trained classification CNN is used to classify the road surface part and output the road surface type and confidence. The CNN used in image preprocessing and classification is a deep feedforward neural network, because it has developed rapidly and has a good effect in image classification and target detection. With the continuous development of deep learning technology, the network used in this module can also be continuously updated, thereby continuously improving the accuracy of the results. The two pre-trained CNNs mentioned above both include input layers, convolutional layers, pooling layers, fully connected layers and output layers, wherein there are multiple convolutional layers and pooling layers, and the difference is that the training data and output parameters are different. For the pre-trained CNN used to extract the road surface part in the picture, the picture data required is the data after the annotation and operation, while the pre-trained CNN used for classification requires only the picture data whose size meets the requirements of the network input layer.

[0055] In step S220, obtaining the first road adhesion coefficient of the current road surface according to vehicle dynamics includes: obtaining the braking force limited slip slip rate based on ABS point braking slip rate control; obtaining the driving force limited slip control slip rate based on the motor drive torque limited slip control; and obtaining the first road adhesion coefficient based on the braking force limited slip slip rate and the driving force limited slip control slip rate.

[0056] In one embodiment, referring to Figure 3 As shown in the figure, dynamic estimation can be performed through braking control or driving control. Based on the dynamic modeling of the four-wheel independent drive vehicle, the four wheels have separate control units, so the road surface judgment of the four wheels can be performed independently, and correct estimation can still be performed when the tires on both sides receive braking and driving control respectively. This module first performs tire and vehicle dynamics modeling, and then needs to receive sensor signals such as wheel speed signals, brake pedal signals, throttle signals, EPS steering angle signals, IMU signals, vehicle speed estimation signals, motor torque signals, etc. The dynamic adhesion coefficient μ1 of the current road surface is estimated using the acquired wheel speed signals, IMU signals, wheel end acceleration signals, etc.

[0057] In one embodiment, when the road surface type is included in a road surface type-road surface adhesion coefficient mapping table, the road surface adhesion coefficient μ2 is obtained by looking up the road surface type-road surface adhesion coefficient mapping table based on the road surface type. The road surface type-road surface adhesion coefficient mapping table is as follows: Figure 4As shown, the road surface type-road surface adhesion coefficient mapping table includes a plurality of data pairs corresponding to the road surface type and the second road surface adhesion coefficient. Then directly execute step S240 to obtain the final road surface adhesion coefficient μ3 based on the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2 obtained by looking up the table. In one embodiment, the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2 obtained by looking up the table are input into the arbitration module, and one of the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2 obtained by looking up the table is selected as the final road surface adhesion coefficient μ3 according to the preset rules of the arbitration module. In one embodiment, the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2 obtained by looking up the table are input into the arbitration module, and according to the weight coefficients corresponding to the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2 obtained by looking up the table, the weight sum of the two is determined as the final road surface adhesion coefficient μ3.

[0058] When the road surface type is not included in the road surface type-road surface adhesion coefficient mapping table, step S230 is first performed to obtain a second road surface adhesion coefficient of the current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface.

[0059] Exemplarily, obtaining the second road adhesion coefficient of the current road based on the one or more images of the current road and the first road adhesion coefficient of the current road includes: inputting the one or more images of the current road and the first road adhesion coefficient of the current road into a deep learning model to obtain the output second road adhesion coefficient of the current road. Each frame of the image and the first road adhesion coefficient at the same time constitute a data pair.

[0060] Exemplarily, the pavement type of the current pavement and the second pavement adhesion coefficient of the current pavement are updated online to the pavement type-pavement adhesion coefficient mapping table to obtain an online updated pavement type-pavement adhesion coefficient mapping table.

[0061] In one embodiment, when the above-mentioned road surface type cannot be found in the road surface type-road surface adhesion coefficient mapping table, the visual module sends a switch signal to start the online update module, and the data storage module starts to collect the video information of the vehicle-mounted camera and the road surface adhesion coefficient of the dynamic module estimation module at the same time, and stores it in the data storage module in the form of data pairs. Then the data learning module uses the data pairs for online training and learning, and finally outputs a new road surface type-road surface adhesion coefficient mapping table, and updates it to the original mapping table. After the mapping table is updated, in order to ensure its accuracy, the data storage module and the learning module need to continue to update for a period of time before stopping the operation (this process is achieved by setting the error preset value, etc.), and upload the stored data to the cloud as a data reserve. At the same time, the storage module needs to be cleared so that the function can run normally next time.

[0062] Next, step S240 is executed to obtain a third road surface adhesion coefficient based on the first road surface adhesion coefficient and the second road surface adhesion coefficient. In one embodiment, the final road surface adhesion coefficient μ3 is obtained based on the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2, wherein the road surface adhesion coefficient μ2 can be obtained by the deep learning model in step S230, or by looking up the updated road surface type-road surface adhesion coefficient mapping table. In one embodiment, the dynamic adhesion coefficient μ1 and the road surface adhesion coefficient μ2 obtained by looking up the table are input into the arbitration module, and the arbitration module is processed to obtain the final road surface adhesion coefficient μ3.

[0063] The present invention also provides a road surface recognition system, comprising:

[0064] A road surface acquisition module, used to acquire one or more images of the current road surface through a vehicle-mounted visual device, and obtain a road surface type of the current road surface based on the one or more images of the current road surface;

[0065] A first road surface adhesion coefficient acquisition module, used for obtaining a first road surface adhesion coefficient of a current road surface according to vehicle dynamics;

[0066] A second road surface adhesion coefficient acquisition module, configured to obtain a second road surface adhesion coefficient of a current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface when the road surface type is not included in a road surface type-road surface adhesion coefficient mapping table;

[0067] The third road surface adhesion coefficient acquisition module is used to obtain a third road surface adhesion coefficient based on the first road surface adhesion coefficient and the second road surface adhesion coefficient.

[0068] In an embodiment of the present invention, the road surface acquisition module obtains the road surface type of the current road surface based on one or more images of the current road surface, including: segmenting the one or more images of the current road surface one by one, extracting the road surface part in the one or more images; inputting the road surface part in the one or more images into a deep learning model, and obtaining the output road surface type of the current road surface. The deep learning model includes a decision tree, a random forest, a deep convolutional neural network, a combination of a deep convolutional neural network and a recursive neural network and their variants, or a combination of a deep convolutional neural network and a conditional random field.

[0069] In an embodiment of the present invention, the first road adhesion coefficient acquisition module obtains the first road adhesion coefficient of the current road surface according to vehicle dynamics, including: obtaining the braking force limited slip slip rate based on ABS point braking slip rate control; obtaining the driving force limited slip control slip rate based on the motor drive torque limited slip control; and obtaining the first road adhesion coefficient based on the braking force limited slip slip rate and the driving force limited slip control slip rate.

[0070] In an embodiment of the present invention, the second road surface adhesion coefficient acquisition module obtains the second road surface adhesion coefficient of the current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface, including: inputting one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface into a deep learning model, and obtaining the second road surface adhesion coefficient of the current road surface output by the deep learning model.

[0071] In an embodiment of the present invention, the third road adhesion coefficient acquisition module obtains the final road adhesion coefficient μ3 based on the dynamic adhesion coefficient μ1 and the road adhesion coefficient μ2, wherein the road adhesion coefficient μ2 can be obtained by the deep learning model in step S230, or by looking up the updated road type-road adhesion coefficient mapping table. In one embodiment, the dynamic adhesion coefficient μ1 and the road adhesion coefficient μ2 obtained by looking up the table are input into the arbitration module, and the arbitration module processes them to obtain the final road adhesion coefficient μ3.

[0072] In addition, according to an embodiment of the present invention, a computer-readable storage medium is also provided, on which program instructions are stored, and when the program instructions are executed by a computer or a processor, the corresponding steps of the road surface recognition method of the embodiment of the present invention are executed, and the corresponding modules in the road surface recognition system according to the embodiment of the present invention are implemented. The computer-readable storage medium may include, for example, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media, for example, one computer-readable storage medium contains a computer-readable program code for randomly generating a sequence of action instructions, and another computer-readable storage medium contains a computer-readable program code for controlling crystal growth.

[0073] According to the road surface recognition method, system, computer-readable storage medium, electronic device and vehicle provided by the present invention, when the road surface type of the current road surface is not included in the existing road surface type-road surface adhesion coefficient mapping table, the second road surface adhesion coefficient of the current road surface is obtained based on one or more images of the current road surface obtained by the on-board visual device and the first road surface adhesion coefficient of the current road surface obtained according to vehicle dynamics, and the road surface type of the current road surface and the second road surface adhesion coefficient of the current road surface are updated online to the existing road surface type-road surface adhesion coefficient mapping table to obtain an online updated road surface type-road surface adhesion coefficient mapping table, and further obtain the third road surface adhesion coefficient based on both the first road surface adhesion coefficient and the second road surface adhesion coefficient.

[0074] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0075] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0077] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0078] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0079] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0080] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0081] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some modules according to the embodiments of the present application. The application can also be implemented as a device program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0082] It should be noted that the above embodiments illustrate rather than limit the present application, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0083] The above is only a specific implementation method or an explanation of a specific implementation method of the present application, and the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A road surface recognition method, characterized in that: include: Acquire one or more images of the current road surface through a vehicle-mounted visual device, and obtain a road surface type of the current road surface based on the one or more images of the current road surface; Obtaining a first road adhesion coefficient of the current road surface according to vehicle dynamics; When the road surface type is not included in the road surface type-road surface adhesion coefficient mapping table, obtaining a second road surface adhesion coefficient of the current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface; A third road surface adhesion coefficient is obtained based on the first road surface adhesion coefficient and the second road surface adhesion coefficient.

2. The road surface recognition method according to claim 1, characterized in that: Obtaining a second road surface adhesion coefficient of the current road surface based on the one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface comprises: One or more images of the current road surface and a first road surface adhesion coefficient of the current road surface are input into a deep learning model to obtain a second road surface adhesion coefficient of the current road surface output by the deep learning model.

3. The road surface recognition method according to claim 1, characterized in that: Obtaining the road surface type of the current road surface based on the one or more images of the current road surface includes: Segmenting the one or more images of the current road surface one by one to extract road surface portions from the one or more images; The road surface portion in the one or more images is input into a classifier to obtain an output road surface type of the current road surface.

4. The road surface recognition method according to claim 2, characterized in that: Also includes: The road surface type of the current road surface and the second road surface adhesion coefficient of the current road surface are updated online to the road surface type-road surface adhesion coefficient mapping table to obtain an online updated road surface type-road surface adhesion coefficient mapping table.

5. The road surface recognition method according to claim 1, characterized in that: Obtaining the first road adhesion coefficient of the current road surface according to vehicle dynamics includes: Based on the ABS point brake slip rate control, the braking force limited slip rate is obtained; Obtaining a driving force limited slip control slip ratio based on the motor driving torque limited slip control; The first road surface adhesion coefficient is obtained based on the braking force limited slip slip ratio and the driving force limited slip control slip ratio.

6. The road surface recognition method according to claim 1, characterized in that: Each image of the one or more images and the first road adhesion coefficient at the same time constitute a data pair.

7. The road surface recognition method according to claim 1, characterized in that: The road surface type-road surface adhesion coefficient mapping table includes a plurality of data pairs corresponding to road surface types and second road surface adhesion coefficients in a one-to-one manner.

8. A road surface recognition system, characterized in that: include: A road surface acquisition module, used to acquire one or more images of the current road surface through a vehicle-mounted visual device, and obtain a road surface type of the current road surface based on the one or more images of the current road surface; A first road surface adhesion coefficient acquisition module, used for obtaining a first road surface adhesion coefficient of a current road surface according to vehicle dynamics; A second road surface adhesion coefficient acquisition module, configured to, when the road surface type is not included in a road surface type-road surface adhesion coefficient mapping table, obtain a second road surface adhesion coefficient of the current road surface based on one or more images of the current road surface and the first road surface adhesion coefficient of the current road surface; The third road surface adhesion coefficient acquisition module is used to obtain a third road surface adhesion coefficient based on the first road surface adhesion coefficient and the second road surface adhesion coefficient.

9. A computer-readable storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the road surface recognition method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is used to execute the road surface recognition method according to any one of claims 1 to 7.

11. A vehicle, characterized in that: The electronic device comprising the electronic device described in claim 10.

Images