Road surface state recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a road surface state recognition method and device, electronic equipment and a storage medium, and relates to the technical field of computers.The method comprises the steps that signals of vehicle tires in a target time period are collected, and the signals comprise multiple pieces of target data; processing the signal based on the target data to obtain a spectrogram corresponding to the signal; determining a target value based on the root-mean-square value of the frequency domain signal in the spectrogram in at least one frequency band; the frequency band corresponds to one modal characteristic of the tire; and recognizing the road surface state based on the target value. Through the root-mean-square value of the spectrogram corresponding to the signal of the vehicle tire in the target time period in at least one frequency band, in combination with the modal characteristics of the tire, efficient and accurate recognition of the road surface state in the target time period is realized, and the speed and accuracy of road surface state recognition are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a road surface condition recognition method, device, electronic device, and storage medium. Background Art

[0002] In the modern automotive industry, the application of intelligent tire sensors has gradually increased, which are used to monitor tire pressure, temperature, and other key performance parameters. These sensors provide important data support for improving vehicle safety, optimizing fuel efficiency, and enhancing the driving experience. In recent years, with the development of autonomous driving technology, how to use intelligent tire sensors to identify road surface conditions in real time has become a research hotspot. Road surface recognition technology can help vehicles better adapt to various driving environments, thereby ensuring driving safety and efficiency.

[0003] The existing intelligent tire sensor technology mainly focuses on using pressure or temperature sensors, which can provide certain data for monitoring tire conditions. However, in complex driving environments, such as rainy or snowy weather or different types of road surfaces (such as asphalt, gravel, dirt, etc.), these sensors still have obvious deficiencies in the accuracy and response speed of road surface recognition, limiting their adaptability in diverse environments. In addition, it often needs to be integrated with other vehicle systems, such as dynamic stability control systems, which increases system complexity and cost.

[0004] In terms of real-time road surface recognition, the existing technology lacks effective algorithms to integrate and analyze the data collected from tire sensors, resulting in insufficient vehicle adaptability in changing road conditions. Moreover, it fails to effectively identify rapid changes in road surface conditions within a short period of time, such as sudden changes from rough to smooth, which is particularly important under extreme climate conditions.

[0005] Therefore, how to achieve efficient and accurate recognition of road surface conditions in diverse environments and road surface conditions is an urgent problem to be solved. Summary of the Invention

[0006] The present invention provides a road surface condition recognition method, device, electronic device, and storage medium to solve the problem of how to achieve efficient and accurate recognition of road surface conditions in diverse environments and road surface conditions.

[0007] The present invention provides a road surface condition recognition method, including: Collect signals of vehicle tires within a target time period, where the signals include multiple target data; Based on each of the target data, process the signals to obtain a spectrogram corresponding to the signals; Based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band, determine a target value; the frequency band corresponds to a modal feature of the tire. Identify the road surface condition based on the target value.

[0008] According to a road surface condition identification method provided by the present invention, determining the target value based on the root mean square values of the frequency domain signals in at least one frequency band in the spectrogram includes: Multiply the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band to obtain the target value.

[0009] According to a road surface condition identification method provided by the present invention, identifying the road surface condition based on the target value includes: Judge the range where the target value is located; When the target value is in the first range, identify the road surface condition as rough asphalt; When the target value is in the second range, identify the road surface condition as cement road; When the target value is in the third range, identify the road surface condition as smooth asphalt.

[0010] According to a road surface condition identification method provided by the present invention, processing the signal based on each of the target data to obtain the spectrogram corresponding to the signal includes: Determine at least one peak position of each of the target data; Based on each of the peak positions, split the signal into at least two segments of signals; Based on the at least two segments of signals, determine the spectrogram corresponding to the signal.

[0011] According to a road surface condition identification method provided by the present invention, determining the spectrogram corresponding to the signal based on the at least two segments of signals includes: For each segment of signal, determine the target frequency domain signal corresponding to the segment of signal; Based on the target frequency domain signals respectively corresponding to all segments of signals, determine the spectrogram corresponding to the signal.

[0012] According to a road surface condition identification method provided by the present invention, determining the target frequency domain signal corresponding to each segment of signal includes: Window each segment of signal to obtain the windowed signal; Zero-pad the windowed signal; Perform Fourier transform on the zero-padded signal to obtain the target frequency domain signal corresponding to each segment of signal.

[0013] According to a road surface condition identification method provided by the present invention, determining the spectrogram corresponding to the signal based on the target frequency domain signals respectively corresponding to all segments of signals includes: Average the target frequency-domain signals corresponding to all segment signals to obtain the spectrogram corresponding to the signal.

[0014] The present invention also provides a road surface state recognition device, including: An acquisition module, configured to acquire signals of a vehicle tire within a target time period, where the signals include a plurality of target data; A processing module, configured to process the signals based on each of the target data to obtain the spectrogram corresponding to the signals; A determination module, configured to determine a target value based on the root mean square values of the frequency-domain signals in at least one frequency band in the spectrogram; the frequency band corresponds to a modal feature of the tire; An identification module, configured to identify the road surface state based on the target value.

[0015] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the road surface state recognition method described in any one of the above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the road surface state recognition method described in any one of the above is implemented.

[0017] The road surface state recognition method, device, electronic device, and storage medium provided by the present invention collect signals of a vehicle tire within a target time period, where the signals include a plurality of target data; process the signals based on each of the target data to obtain the spectrogram corresponding to the signals; determine a target value based on the root mean square values of the frequency-domain signals in at least one frequency band in the spectrogram; the frequency band corresponds to a modal feature of the tire; identify the road surface state based on the target value, and the frequency band corresponds to a modal feature of the tire. By using the root mean square values of the spectrogram corresponding to the signals of the vehicle tire within the target time period in at least one frequency band, and combining the modal features of the tire itself, the efficient and accurate recognition of the road surface state within the target time period is realized, and the speed and accuracy of road surface state recognition are improved. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1It is one of the schematic flowcharts of the road surface state recognition method provided by the present invention.

[0020] Figure 2 It is a schematic diagram of the spectrogram corresponding to the signal provided by the present invention.

[0021] Figure 3 It is a comparative schematic diagram of the spectrograms corresponding to the signals under different road surface states provided by the present invention.

[0022] Figure 4 It is a schematic diagram of each segment of the signal after splitting provided by the present invention.

[0023] Figure 5 It is a schematic diagram of the windowed signal provided by the present invention.

[0024] Figure 6 It is the second schematic flowchart of the road surface state recognition method provided by the present invention.

[0025] Figure 7 It is a schematic structural diagram of the road surface state recognition device provided by the present invention.

[0026] Figure 8 It is a schematic physical structure diagram of the electronic device provided by the present invention. Detailed implementation manners

[0027] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] The following combines Figures 1-6 to describe the road surface state recognition method of the present invention.

[0029] Figure 1 It is one of the schematic flowcharts of the road surface state recognition method provided by the present invention. As Figure 1 shown, the method includes Step 101 to Step 104.

[0030] Step 101: Collect the signals of the vehicle tires within the target time period, and the signals include a plurality of target data.

[0031] It should be noted that the road surface state recognition method provided by the present invention can be applied to the road surface state recognition scenario based on intelligent tire sensors; the execution subject of this method can be a road surface state recognition device, such as an electronic device, or a control module in the road surface state recognition device for executing the road surface state recognition method.

[0032] Specifically, an intelligent tire sensor, such as an acceleration chip sensor, is pasted inside the vehicle tire. The sampling frequency of the sensor is 1600 Hz. To ensure the real-time feedback of the road surface condition, data with a length of a target time period (for example, 1 second (s)) is selected as the analysis duration for one frame for road surface condition recognition.

[0033] The intelligent tire sensor collects the signals of the vehicle tire within the target time period. The signals include multiple target data, and the target data is the acceleration in the z direction inside the tire. For example, the signals within 1 s include 1600 data points.

[0034] It should be noted that since sensors such as acceleration chips are always attached to the inner wall of the tire during the tire rolling process, the reference value of the radial acceleration is the centripetal acceleration, and the centripetal acceleration is equal to the product of the inner radius of the tire and the rolling speed. Based on the centripetal acceleration, the radial acceleration shows a fluctuating characteristic: within each period, there are two maximum values; between the two acceleration maximum value peaks, there is a minimum value trough. The reason for this phenomenon is the contact deformation between the tire and the road surface. When the acceleration sensor is not in contact with the road surface, the radial acceleration is only the centripetal acceleration; when it is within the range of complete contact with the road surface, the sensor is approximately in translational motion and the radius is infinite, so the centripetal acceleration is approximately zero, corresponding to the minimum value trough of the radial acceleration; at the front and rear ends of grounding, the elastic deformation of the tread rubber increases rapidly and the radius of curvature decreases, resulting in a sudden increase in the radial acceleration, corresponding to the two maximum value peaks of the radial acceleration.

[0035] Step 102: Based on each of the target data, process the signal to obtain the spectrogram corresponding to the signal.

[0036] Specifically, based on each target data, processing the signal can obtain the spectrogram corresponding to the signal. The spectrogram represents the amplitude distribution of the vehicle tire in the frequency domain. Figure 2 It is a schematic diagram of the spectrogram corresponding to the signal provided by the present invention. As Figure 2 shown, in the spectrogram, the frequency corresponding to the highest peak is the rotation frequency of the tire, that is, the number of turns the tire makes per second.

[0037] Figure 3 It is a comparison schematic diagram of the spectrograms corresponding to the signals under different road surface conditions provided by the present invention. As Figure 3 shown, through the comparison of the spectral curves, it is close to the actual perception, that is, the rough asphalt road surface has the greatest excitation on the tire, followed by the cement road, and then the smooth asphalt.

[0038] Step 103: Determine the target value based on the root mean square values of the frequency domain signals in at least one frequency band in the spectrogram; the frequency band corresponds to a modal characteristic of the tire.

[0039] Specifically, the frequency band corresponds to a modal characteristic of the tire. For example, the frequency bands are 50 - 100 Hz, 200 - 250 Hz, or 300 - 500 Hz. For vehicle tires (e.g., car tires), there are 3 important modes within 500 Hz, and each mode corresponds to a different natural frequency, which are respectively the radial first - order mode below 100 Hz, the cavity mode of 200 - 250 Hz, and the tread depression mode of 300 - 500 Hz. By conducting a modal test on the tire, the peaks of the 3 important modes of the tire can be obtained.

[0040] Based on the root - mean - square (RMS) values of the frequency - domain signals in at least one frequency band in the spectrogram, the target value can be determined. The target value is the root - mean - square sum (RMSS), and the target value is used as a numerical index for road surface discrimination.

[0041] It should be noted that different road surfaces have different excitations on the tire. Therefore, the energy branches of the three important frequency bands are also different. The 3 different road surface states can be distinguished by the magnitudes of the energy values of the three important frequency bands: 50 - 100 Hz, 200 - 250 Hz, and 300 - 500 Hz.

[0042] Step 104: Identify the road surface state based on the target value.

[0043] Specifically, based on the target value, the road surface state can be identified; where the road surface state includes any one of the following: rough asphalt, cement road, and smooth asphalt.

[0044] The road surface state recognition method provided by the present invention collects the signals of the vehicle tire within the target time period, and the signals include a plurality of target data; based on each of the target data, the signals are processed to obtain the spectrogram corresponding to the signals; based on the root - mean - square values of the frequency - domain signals in at least one frequency band in the spectrogram, the target value is determined; the frequency band corresponds to a modal characteristic of the tire; based on the target value, the road surface state is identified, and the frequency band corresponds to a modal characteristic of the tire. By using the root - mean - square values of the spectrogram corresponding to the signals of the vehicle tire within the target time period in at least one frequency band, combined with the modal characteristics of the tire itself, the efficient and rapid recognition of the road surface state within the target time period is realized, and the speed and accuracy of road surface state recognition are improved.

[0045] Optionally, the specific implementation manner of the above - mentioned step 102 includes: (1) Determine at least one peak position of each of the target data.

[0046] Specifically, based on each piece of target data included in the signal, at least one peak position of each piece of target data can be determined, where the peak position is a negative peak position.

[0047] (2) Based on each of the peak positions, split the signal into at least two segments of signals.

[0048] Specifically, based on each peak position, the signal can be split into at least two segments of signals. For example, if 9 negative peak positions are found, denoted as P1, P2, P3, …, P9, then the signal is split into P1~P2, P2~P3, …, P8~P9, a total of 8 segments of signals, as Figure 4 shown, Figure 4 which is a schematic diagram of each segment of the signal after splitting provided by the present invention.

[0049] (3) Based on the at least two segments of signals, determine the spectrogram corresponding to the signal.

[0050] Specifically, based on at least two segments of signals, the spectrogram corresponding to the signal can be further determined.

[0051] Optionally, the specific implementation manner of the above step (3) includes: For each segment of signal, determine the target frequency-domain signal corresponding to each segment of signal; based on the target frequency-domain signals respectively corresponding to all segments of signals, determine the spectrogram corresponding to the signal.

[0052] Specifically, the target frequency-domain signal can be the absolute value of the amplitude data ranked in the top 256. For each segment of signal, the target frequency-domain signal corresponding to each segment of signal can be determined; then based on the target frequency-domain signals respectively corresponding to all segments of signals, the spectrogram corresponding to the signal can be determined.

[0053] Optionally, determining the target frequency-domain signal corresponding to each segment of signal includes: Apply a window to each segment of signal to obtain the windowed signal; zero-pad the windowed signal; perform Fourier transform on the zero-padded signal to obtain the target frequency-domain signal corresponding to each segment of signal.

[0054] It should be noted that due to the large peak energy caused by the tire contact area, which is similar to a relatively large pulse signal, due to the shape and periodicity of the pulse, additional spectral components will be introduced on the basis of the spectrum of the original signal, and these components are mainly concentrated at the multiple positions of the pulse emission frequency; due to the large energy at the tire contact and lift-off, this part of the energy causes great interference to the spectrum of the road surface response of the spectrum itself of the road surface. Therefore, it is necessary to eliminate the contact end and lift-off end parts.

[0055] Specifically, each segment of the signal is windowed to obtain the windowed signal. For example, a Hanning window is applied to each segment of the split signal. After applying the Hanning window, the signal at the negative peak position of each segment of the signal is set to zero, that is, the ground terminal part is set to zero, as Figure 5 shown Figure 5 is a schematic diagram of the windowed signal provided by the present invention.

[0056] To ensure that the length of each segment of the signal after Fourier transform is the same, zero-padding is performed on the windowed signal, that is, 0s are added at the end of the data so that the length of each segment of the windowed signal is equal to 512. Then, Fourier transform is performed on the zero-padded signal to obtain the target frequency-domain signal corresponding to each segment of the signal, that is, the absolute value of the amplitude data ranked in the top 256.

[0057] Optionally, determining the spectrogram corresponding to the signal based on the target frequency-domain signals respectively corresponding to all segments of the signal includes: Averaging the target frequency-domain signals respectively corresponding to all segments of the signal to obtain the spectrogram corresponding to the signal.

[0058] Specifically, by averaging the target frequency-domain signals respectively corresponding to all segments of the signal, the spectrogram corresponding to the signal can be obtained.

[0059] In this application, by determining at least one peak position of each target data, the reason for the mutation characteristics of the Z-axis acceleration signal inside the tire is analyzed, and then the interference of the mutation signal on the spectral characteristics of the acceleration signal is analyzed, so as to improve the speed and accuracy of road surface state recognition.

[0060] Optionally, the specific implementation manner of the above step 103 includes: Multiplying the root mean square values of the frequency-domain signals in the spectrogram in at least one frequency band to obtain the target value.

[0061] Specifically, based on the frequency-domain signals in the spectrogram, the root mean square values in at least one frequency band are calculated respectively. For example, the root mean square values in the frequency bands of 50 - 100 Hz, 200 - 250 Hz, and 300 - 500 Hz are calculated respectively and denoted as RMS1, RMS2, and RMS3. Then, multiplying the root mean square values in at least one frequency band can obtain the target value RMSS.

[0062] To amplify the differences among the three road surfaces, the target value can be amplified, for example, amplified 100 times.

[0063] Optionally, the specific implementation manner of the above step 104 includes: When the target value is within the first range, identify the road surface condition as rough asphalt; when the target value is within the second range, identify the road surface condition as cement road; when the target value is within the third range, identify the road surface condition as smooth asphalt.

[0064] Specifically, the first range is between 200 and 250, the second range is between 150 and 200, and the third range is between 50 and 100. Determine the range where the target value is located; when the target value is within the first range (between 200 and 250), identify the road surface condition as rough asphalt; when the target value is within the second range (between 150 and 200), identify the road surface condition as cement road; when the target value is within the third range (between 50 and 100), identify the road surface condition as smooth asphalt.

[0065] When the vehicle is driving on different road surfaces, the target value (RMSS value) changes in real time. By collecting data only within the target time period (for example, 1 s), the road surface condition can be identified.

[0066] Figure 6 is the second schematic diagram of the process of the road surface condition identification method provided by the present invention. As Figure 6 shown, the method includes step 601 - step 608.

[0067] Step 601: Collect the signals of the vehicle tires within the target time period. The signals include a plurality of target data.

[0068] Step 602: Determine at least one peak position of each target data; based on each peak position, split the signal into at least two segments of signals.

[0069] Step 603: For each segment of signal, apply a window to each segment of signal to obtain the windowed signal; zero-pad the windowed signal; perform Fourier transform on the zero-padded signal to obtain the target frequency-domain signal corresponding to each segment of signal.

[0070] Step  604: Average the target frequency-domain signals corresponding to all segments of signals to obtain the spectrogram corresponding to the signal.

[0071] Step 605: Multiply the root mean square values of the frequency-domain signals in the spectrogram in at least one frequency band to obtain the target value.

[0072] Step 606: When the target value is within the first range, identify the road surface condition as rough asphalt.

[0073] Step 607: When the target value is within the second range, identify the road surface condition as cement road.

[0074] Step 608, when the target value is within the third range, identify the road surface condition as smooth asphalt.

[0075] The road surface condition recognition method provided by the present invention has a fast response. It can quickly identify different road surface conditions within only the target time period (1 second), and has high computing efficiency. It can be integrated into the sensor for edge computing to further accelerate the response speed.

[0076] Next, the road surface condition recognition device provided by the present invention will be described. The road surface condition recognition device described below can be correspondingly referred to the road surface condition recognition method described above.

[0077] Figure 7 is a schematic structural diagram of the road surface condition recognition device provided by the present invention. As Figure 7 shown, the road surface condition recognition device 700 includes: a collection module 701, a processing module 702, a determination module 703, and an identification module 704; wherein, The collection module 701 is configured to collect signals of the vehicle tire within the target time period, and the signals include a plurality of target data; The processing module 702 is configured to process the signals based on each of the target data to obtain a spectrogram corresponding to the signals; The determination module 703 is configured to determine a target value based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band; the frequency band corresponds to a modal characteristic of the tire; The identification module 704 is configured to identify the road surface condition based on the target value.

[0078] The road surface condition recognition device provided by the present invention collects signals of the vehicle tire within the target time period, and the signals include a plurality of target data; processes the signals based on each of the target data to obtain a spectrogram corresponding to the signals; determines a target value based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band; the frequency band corresponds to a modal characteristic of the tire; and identifies the road surface condition based on the target value, and the frequency band corresponds to a modal characteristic of the tire. By using the root mean square values of the spectrogram corresponding to the signals of the vehicle tire within the target time period in at least one frequency band, combining the modal characteristics of the tire itself, it realizes the efficient and rapid recognition of the road surface condition within the target time period, and improves the speed and accuracy of road surface condition recognition.

[0079] Optionally, the determination module 703 is specifically configured to: Multiply the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band to obtain the target value.

[0080] Optionally, the identification module 704 is specifically configured to: When the target value is within the first range, identify the road surface condition as rough asphalt; When the target value is within the second range, identify the road surface condition as cement road; When the target value is within the third range, identify the road surface condition as smooth asphalt.

[0081] Optionally, the processing module 702 is specifically configured to: Determine at least one peak position of each of the target data; Based on each of the peak positions, split the signal into at least two segments of signals; Based on the at least two segments of signals, determine the spectrogram corresponding to the signal.

[0082] Optionally, the processing module 702 is further configured to: For each segment of signal, determine the target frequency-domain signal corresponding to each segment of signal; Based on the target frequency-domain signals respectively corresponding to all segments of signals, determine the spectrogram corresponding to the signal.

[0083] Optionally, the processing module 702 is further configured to: Apply a window to each segment of signal to obtain the windowed signal; Pad zeros to the windowed signal; Perform Fourier transform on the zero-padded signal to obtain the target frequency-domain signal corresponding to each segment of signal.

[0084] Optionally, the processing module 702 is further configured to: Average the target frequency-domain signals respectively corresponding to all segments of signals to obtain the spectrogram corresponding to the signal.

[0085] Figure 8 It is a schematic diagram of the physical structure of the electronic device provided by the present invention, as Figure 8As shown in the figure, the electronic device may include: a processor 810, a communications interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communications interface 820, and the memory 830 complete communication with each other through the communication bus 840. The processor 810 may call the logical instructions in the memory 830 to execute the road surface state recognition method, and the method includes: collecting signals of the vehicle tires within a target time period, where the signals include a plurality of target data; based on each of the target data, processing the signals to obtain a spectrogram corresponding to the signals; based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band, determining a target value; the frequency band corresponds to a modal characteristic of the tire; based on the target value, recognizing the road surface state.

[0086] In addition, when the logical instructions in the above-mentioned memory 830 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a 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 causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0087] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is used to execute the road surface state recognition method provided by the above-mentioned methods. The method includes: collecting signals of the vehicle tires within a target time period, where the signals include a plurality of target data; based on each of the target data, processing the signals to obtain a spectrogram corresponding to the signals; based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band, determining a target value; the frequency band corresponds to a modal characteristic of the tire; based on the target value, recognizing the road surface state.

[0088] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0089] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying road surface conditions, characterized in that, Including: Collect signals of a vehicle tire within a target time period, where the signals include multiple target data; Based on each of the target data, process the signals to obtain a spectrogram corresponding to the signals; Based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band, determine a target value; the frequency band corresponds to a modal characteristic of the tire; Based on the target value, identify the road surface condition.

2. The road surface condition recognition method according to claim 1, characterized in that The determining the target value based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band includes: Multiply the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band to obtain the target value.

3. The pavement condition recognition method according to claim 1, wherein The identifying the road surface condition based on the target value includes: When the target value is within a first range, identify the road surface condition as rough asphalt; When the target value is within a second range, identify the road surface condition as cement road; When the target value is within a third range, identify the road surface condition as smooth asphalt.

4. The road surface state recognition method according to any one of claims 1 to 3, characterized in that The processing the signals based on each of the target data to obtain a spectrogram corresponding to the signals includes: Determine at least one peak position of each of the target data; Based on each of the peak positions, split the signals into at least two segments of signals; Based on the at least two segments of signals, determine a spectrogram corresponding to the signals.

5. The pavement condition recognition method according to claim 4, characterized in that, The determining a spectrogram corresponding to the signals based on the at least two segments of signals includes: For each segment of signals, determine a target frequency domain signal corresponding to the each segment of signals; Based on the target frequency domain signals respectively corresponding to all segments of signals, determine a spectrogram corresponding to the signals.

6. The pavement condition recognition method according to claim 5, wherein, The determining a target frequency domain signal corresponding to each segment of signals includes: Window each segment of signals to obtain windowed signals; Pad zeros to the windowed signals; Perform Fourier transform on the signals with padded zeros to obtain a target frequency domain signal corresponding to each segment of signals.

7. The pavement condition recognition method according to claim 5, characterized in that, The determining a spectrogram corresponding to the signals based on the target frequency domain signals respectively corresponding to all segments of signals includes: Average the target frequency domain signals respectively corresponding to all segments of signals to obtain a spectrogram corresponding to the signals.

8. A road surface condition recognition device, characterized in that Including: A collection module for collecting signals of a vehicle tire within a target time period, where the signals include multiple target data; A processing module for processing the signals based on each of the target data to obtain a spectrogram corresponding to the signals; A determination module for determining a target value based on the root mean square values of the frequency domain signals in the spectrogram in at least one frequency band; the frequency band corresponds to a modal characteristic of the tire; An identification module for identifying the road surface condition based on the target value.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the computer program, it implements the road surface condition identification method according to any one of claims 1 to 7.

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, it implements the road surface condition identification method according to any one of claims 1 to 7.

Images