Steering wheel detection method and device, electronic equipment and storage medium

Abstract

The invention provides a steering wheel detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an elastic wave signal collected by an elastic wave sensor array in a vehicle steering wheel, determining a target elastic wave sensor which collects the elastic wave signal according to a preset interference frequency band and an environment noise waveform, carrying out the filtering of the elastic wave signal, and obtaining a filtering result; filtering the steering wheel touch signal to obtain a filtered steering wheel touch signal, performing feature extraction on the steering wheel touch signal to obtain a touch feature, performing touch behavior recognition, determining a touch behavior of a driver on the steering wheel, generating driving prompt information, and performing prompt by adopting the driving prompt information. The elastic wave signal on the steering wheel is captured through the elastic wave sensor array arranged on the steering wheel, the detection precision is improved, the touch behavior of the steering wheel is recognized based on the effective touch signal, and the accuracy of detecting the touch behavior of the driver on the steering wheel is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a steering wheel detection method, device, electronic equipment and storage medium. Background Art

[0002] With the rapid development of automotive intelligence and autonomous driving technology, driving behavior detection has become an important part of improving driving safety. Steering wheel detection, as one of the key functions of driving behavior detection, aims to monitor in real time whether the driver is holding the steering wheel correctly to prevent traffic accidents caused by driver distraction or hands-off control.

[0003] At present, the detection of the driver's driving behavior on the steering wheel is mainly achieved through image detection or the pressure of the hand holding the steering wheel. Specifically, image detection uses a camera to collect video frame data of the driver and the steering wheel, thereby locating the steering wheel image and hand image in a single frame image, and performing image target recognition and detection. It is easily affected by environmental factors such as lighting conditions, occlusion (such as hands being blocked by clothing) or changes in the driver's hand posture; the pressure detection of the hand holding the steering wheel is to collect the hand force signal, steering assist signal and active return status signal on the steering wheel through the traditional pressure sensor on the steering wheel. The detection accuracy of the traditional pressure sensor is low and it cannot detect weak signals generated by the virtual steering wheel. Therefore, the current steering wheel detection method has insufficient detection accuracy and cannot effectively detect the touch on the steering wheel, which affects the accuracy of the driver's detection of the steering wheel driving behavior. Summary of the Invention

[0004] In view of this, the present invention aims to propose a steering wheel detection method, device, electronic device and storage medium to solve the problem that the current steering wheel detection method has insufficient detection accuracy and cannot effectively detect touch on the steering wheel, thereby affecting the driver's detection accuracy of the steering wheel driving behavior.

[0005] According to a first aspect of the present invention, a steering wheel detection method is provided, the method comprising: Acquiring an elastic wave signal collected by an elastic wave sensor array in a vehicle steering wheel; wherein the elastic wave sensor array includes a plurality of elastic wave sensors uniformly disposed on a steering wheel rim; According to a preset interference frequency band and an ambient noise waveform, and determining a target elastic wave sensor that has collected the elastic wave signal, filtering the elastic wave signal to obtain a filtered steering wheel touch signal; Extracting features from the steering wheel touch signal to obtain touch features, wherein the touch features include a touch signal peak value, a touch duration, and a touch signal frequency band; performing touch behavior recognition based on the touch signal peak value, the touch duration, and the touch signal frequency band to determine the driver's touch behavior on the steering wheel; wherein the touch behavior includes at least one of rigidly controlling the steering wheel, lightly touching the steering wheel, and hands-free driving; Driving prompt information is generated according to the touch behavior, and the driving prompt information is used for prompting.

[0006] Optionally, obtaining the elastic wave signal collected by the elastic wave sensor array in the vehicle steering wheel includes: In response to detecting that the vehicle is in an unparked state, an elastic wave sensor array in a steering wheel of the vehicle is used to detect an elastic wave signal of the steering wheel; Acquire elastic wave signals collected by each elastic wave sensor in the elastic wave sensor array.

[0007] Optionally, filtering the elastic wave signal based on a preset interference frequency band and an ambient noise waveform, and determining a target elastic wave sensor that has collected the elastic wave signal to obtain a filtered steering wheel touch signal includes: Identifying interference frequency band noise and environmental noise in the elastic wave signal according to a preset interference frequency band and environmental noise waveform; determining a target elastic wave sensor that has collected the elastic wave signal, and determining whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal; Interference frequency band noise, environmental noise, and invalid elastic wave signals in the elastic wave signal are filtered to obtain a filtered steering wheel touch signal.

[0008] Optionally, the determining the target elastic wave sensor that has collected the elastic wave signal and judging whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal includes: determining the number of target elastic wave sensors that have collected the elastic wave signal; If the number of the target elastic wave sensor is one, it is determined that the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal.

[0009] Optionally, after determining the number of target elastic wave sensors that have collected the elastic wave signals, the method further includes: If the number of the target elastic wave sensors is greater than one, obtaining the position coordinates and signal acquisition time of the target elastic wave sensors; Calculating the acquisition delay of the elastic wave signal acquired by the target elastic wave sensor according to the signal acquisition time; According to the position coordinates and the acquisition delay, it is determined whether the elastic wave signal acquired by the target elastic wave sensor is an invalid elastic wave signal.

[0010] Optionally, the feature extraction of the steering wheel touch signal to obtain a touch feature, wherein the touch feature includes a touch signal peak value, a touch duration, and a touch signal frequency band, including: Extracting spectrum features of the steering wheel touch signal to obtain a touch signal peak and a touch signal frequency band; Perform time domain feature extraction on the steering wheel touch signal, determine the duration of the steering wheel touch signal, and obtain the touch duration.

[0011] Optionally, the touch behavior recognition is performed based on the touch signal peak value, the touch duration, and the touch signal frequency band to determine the driver's touch behavior on the steering wheel; wherein the touch behavior includes at least one of rigidly controlling the steering wheel, lightly touching the steering wheel, and hands-free driving, including: If the touch signal peak value, the touch duration, and the touch signal frequency band are less than a preset light touch threshold, it is determined that the driver's touch behavior on the steering wheel is hands-free driving; If the touch signal peak value, the touch duration, and the touch signal frequency band are greater than or equal to a preset light touch threshold and less than a preset rigidity control threshold, it is determined that the driver's touch behavior on the steering wheel is a light touch on the steering wheel; If the touch signal peak value, the touch duration, and the touch signal frequency band are greater than or equal to the preset rigid control threshold, it is determined that the driver's touch behavior on the steering wheel is a rigid control steering wheel.

[0012] According to a second aspect of the present invention, a steering wheel detection device is provided, the device comprising: A signal acquisition module, configured to acquire elastic wave signals collected by an elastic wave sensor array in a vehicle steering wheel; wherein the elastic wave sensor array comprises a plurality of elastic wave sensors uniformly disposed on a steering wheel rim; Signal filtering processing is used to filter the elastic wave signal according to a preset interference frequency band and environmental noise waveform, and to determine the target elastic wave sensor that collected the elastic wave signal, to obtain a filtered steering wheel touch signal; A feature extraction module, configured to extract features from the steering wheel touch signal to obtain touch features; wherein the touch features include a touch signal peak value, a touch duration, and a touch signal frequency band; a behavior recognition module, configured to identify touch behavior based on the touch signal peak value, the touch duration, and the touch signal frequency band, and determine the driver's touch behavior on the steering wheel; the touch behavior includes at least one of rigid steering wheel control, light steering wheel touch, and hands-free driving; A prompt generation module is used to generate driving prompt information according to the touch behavior and use the driving prompt information for prompting.

[0013] According to another aspect of the present invention, there is provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the steering wheel detection method as described above.

[0014] According to another aspect of the present invention, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the steering wheel detection method described above are implemented.

[0015] The steering wheel detection method provided by an embodiment of the present invention obtains an elastic wave signal collected by an elastic wave sensor array in a vehicle steering wheel, where the elastic wave sensor array includes multiple elastic wave sensors evenly deployed on the steering wheel rim. The elastic wave signal is filtered according to a preset interference frequency band and environmental noise waveform, and a target elastic wave sensor that collects the elastic wave signal is determined to obtain a filtered steering wheel touch signal. Feature extraction is performed on the steering wheel touch signal to obtain a touch feature. Touch behavior is identified based on the touch signal peak value, touch duration, and touch signal frequency band to determine the driver's touch behavior on the steering wheel. Driving prompt information is generated based on the touch behavior, and the driving prompt information is used for prompting. The embodiment of the present invention captures the elastic wave signal on the steering wheel by deploying an elastic wave sensor array on the steering wheel, thereby solving the defect that traditional pressure sensors cannot detect weak touch, improving the recognition rate and detection accuracy of hand false touch, and filtering the elastic wave signal based on the interference frequency band, environmental noise and specific sensors, effectively eliminating noise or external interference and invalid signals generated by sensor false triggering, and obtaining the effective elastic wave signal generated by the driver touching the steering wheel, reducing misjudgment caused by noise interference or false triggering, identifying the driver's touch behavior of the steering wheel based on the characteristics of the effective touch signal, and providing timely driving prompts, thereby improving the accuracy of detecting the driver's touch behavior of the steering wheel and further improving driving safety.

[0016] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings: Figure 1 This is a flowchart of the steps of a steering wheel detection method provided by an embodiment of the present invention; Figure 2 yes Figure 1 Flowchart of step 102 in the steering wheel detection method provided by an embodiment of the present invention; Figure 3 yes Figure 1 Flowchart of step 104 in the steering wheel detection method provided by an embodiment of the present invention; Figure 4 1 is a structural diagram of a steering wheel detection device provided by an embodiment of the present invention; Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, each embodiment of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present invention, many technical details are provided to enable the reader to better understand the present invention. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present invention can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with each other and referenced to each other under the premise that there is no contradiction.

[0019] Reference Figure 1 , which shows a flowchart of the steps of a steering wheel detection method provided by an embodiment of the present invention, the method may include: Step 101 : Acquire an elastic wave signal collected by an elastic wave sensor array in a vehicle steering wheel; wherein the elastic wave sensor array includes a plurality of elastic wave sensors uniformly arranged on a steering wheel rim.

[0020] It should be noted that in an embodiment of the present invention, multiple elastic wave sensors are evenly deployed on the rim of the steering wheel to form an elastic wave sensor array. The elastic wave sensor array is used to sensitively capture weak vibration signals caused by the driver's hand touching the steering wheel, such as signals in a virtual state. Specifically, N elastic wave sensors are evenly spaced around the steering wheel rim to form a circular coverage. Multiple elastic wave sensors in the elastic wave sensor array collect elastic wave signals and transmit the collected elastic wave signals to a sensor controller in the vehicle controller for processing and analysis. The elastic wave sensor is a sensor based on the piezoelectric effect or the capacitive effect that can sense tiny vibrations on the surface of an object and convert them into electrical signals. In steering wheel detection, the elastic wave sensor is used to capture the vibration signals generated when the driver touches the steering wheel. The deployment of the elastic wave sensor array is determined by the actual size of the vehicle's steering wheel and the detection requirements. This embodiment does not specifically limit the number of sensors in the elastic wave sensor array or their specific deployment locations.

[0021] Specifically, when the vehicle starts and enters the non-parking state, the vehicle controller automatically activates the elastic wave sensor array on the steering wheel, the elastic wave sensor array enters the working state, and begins to monitor the elastic wave signal on the steering wheel in real time. The sensor controller in the vehicle controller obtains the elastic wave signal collected by each elastic wave sensor in the elastic wave sensor array.

[0022] Step 102 : According to the preset interference frequency band and the ambient noise waveform, and the target elastic wave sensor that has collected the elastic wave signal, the elastic wave signal is filtered to obtain a filtered steering wheel touch signal.

[0023] In an embodiment of the present invention, after the vehicle controller obtains the elastic wave signal collected by the elastic wave sensor array in the vehicle steering wheel, since the collected elastic wave signals are not necessarily generated by the driver's hand touching the steering wheel, there may be noise, external interference or false triggering. In order to reduce the misjudgment caused by noise interference and improve the purity of the elastic wave signal, this embodiment filters the elastic wave signal according to the preset interference frequency band and environmental noise waveform, and determines the target elastic wave sensor that collects the elastic wave signal, and finally obtains the filtered steering wheel touch signal, wherein the target elastic wave sensor is the elastic wave sensor in the elastic wave sensor array that actually collects the elastic wave signal. The number of target elastic wave sensors is determined according to the actual touch situation and can be at least one, which is not limited in this embodiment.

[0024] It should be noted that filtering of elastic wave signals can be divided into frequency domain filtering and spatial domain filtering. The purpose of frequency domain filtering is to remove interference frequency band noise and environmental noise in the signal. Interference frequency band noise includes low-frequency signals and high-frequency signals in preset frequency bands. Environmental noise is pre-collected noise in scenarios such as in-car music, bumpy road vibrations, and in-car human voices. Frequency domain filtering filters the signal through a preset interference frequency band and environmental noise waveform library to obtain a pure elastic wave signal after filtering through the interference frequency band and environmental noise. Spatial domain filtering is implemented based on a determined target elastic wave sensor that collects elastic wave signals. The purpose is to filter out invalid elastic wave signals, which include interference elastic wave signals and elastic wave signals caused by non-driver hands touching the steering wheel.

[0025] In this embodiment, the interference elastic wave signal is judged by the number of target elastic wave sensors, and the elastic wave signal of the non-driver's hand touching the steering wheel is judged by the touch position reflected by the target elastic wave sensor. If the number of target elastic wave sensors that collect the elastic wave signal is one, that is, a single sensor collects the signal, which does not conform to the common sense of the driver touching the steering wheel, it can be determined as an invalid elastic wave signal and spatial filtering is performed; if the distribution of the target sensors that collect the elastic wave signal does not conform to the situation of the driver's hand touching the steering wheel, it can also be determined as an invalid elastic wave signal and spatial filtering is performed to obtain a filtered valid steering wheel touch signal.

[0026] Step 103 : extracting features from the steering wheel touch signal to obtain touch features. The touch features include a touch signal peak value, a touch duration, and a touch signal frequency band.

[0027] In an embodiment of the present invention, after obtaining the filtered steering wheel touch signal, in order to effectively analyze the frequency distribution and energy distribution of the signal and determine the duration of the signal so as to identify the driver's touch behavior on the steering wheel, the vehicle controller of this embodiment extracts features of the steering wheel touch signal to obtain touch features; wherein, the touch features include the touch signal peak value, touch duration and touch signal frequency band.

[0028] Specifically, the signal is subjected to spectral feature extraction to obtain the peak and frequency band information of the touch signal. Time domain feature extraction is performed on the steering wheel touch signal to determine the signal duration, i.e., the touch duration. It should be noted that the touch signal peak reflects the primary energy distribution of the touch signal, the touch signal frequency band reflects the frequency distribution characteristics of the touch signal, and the frequency and energy distribution of the steering wheel touch signal are obtained. The touch duration reflects the duration of the touch behavior.

[0029] Step 104 , performing touch behavior recognition based on the touch signal peak value, touch duration, and touch signal frequency band to determine the driver's touch behavior on the steering wheel; wherein the touch behavior includes at least one of rigidly controlling the steering wheel, lightly touching the steering wheel, and hands-free driving.

[0030] In this embodiment of the present invention, touch behavior recognition is performed based on the extracted touch signal's touch characteristics, namely, the touch signal peak value, touch duration, and touch signal frequency band, to determine whether the driver's touch behavior on the steering wheel is at least one of rigid steering wheel control, light steering wheel touch, and hands-free driving. The touch behavior includes at least one of rigid steering wheel control, light steering wheel touch, and hands-free driving.

[0031] It should be noted that hands-off driving behavior typically exhibits weak signal strength, zero touch duration, and low signal frequency; light touches on the steering wheel typically exhibit moderate signal strength, short duration, and moderate frequency; and rigid steering wheel control typically exhibits strong signal strength, long duration, and high frequency. Therefore, based on this, the touch signal peak value, touch duration, and touch signal frequency range, as well as upper and lower limits, are pre-set for various touch behaviors, allowing touch behavior recognition based on the actual touch signal peak value, touch duration, and touch signal frequency.

[0032] Step 105: Generate driving prompt information according to the touch behavior, and use the driving prompt information for prompting.

[0033] In an embodiment of the present invention, in order to promptly and effectively remind the driver to drive safely based on the real-time detection results of the steering wheel, driving prompt information is generated based on the touch behavior, and the driving prompt information is used for prompting. For example, based on the hands-off driving behavior, if it is determined that the driver is driving with his hands off the steering wheel, the vehicle controller sends a signal to the cockpit domain controller through the CAN bus. The signal includes the driving behavior and the corresponding driving prompt information, so that the cockpit domain controller reminds the driver through text on the display screen, voice, etc. This embodiment does not specifically limit the prompting method of the driving prompt information.

[0034] The steering wheel detection method provided by an embodiment of the present invention obtains an elastic wave signal collected by an elastic wave sensor array in a vehicle steering wheel, where the elastic wave sensor array includes multiple elastic wave sensors evenly deployed on the steering wheel rim. The elastic wave signal is filtered according to a preset interference frequency band and environmental noise waveform, and a target elastic wave sensor that collects the elastic wave signal is determined to obtain a filtered steering wheel touch signal. Feature extraction is performed on the steering wheel touch signal to obtain a touch feature. Touch behavior is identified based on the touch signal peak value, touch duration, and touch signal frequency band to determine the driver's touch behavior on the steering wheel. Driving prompt information is generated based on the touch behavior, and the driving prompt information is used for prompting. The embodiment of the present invention captures the elastic wave signal on the steering wheel by deploying an elastic wave sensor array on the steering wheel, thereby solving the defect that traditional pressure sensors cannot detect weak touch, improving the recognition rate and detection accuracy of hand false touch, filtering the elastic wave signal based on the interference frequency band, environmental noise and specific sensors, effectively eliminating noise or external interference and invalid signals generated by sensor false triggering, and obtaining the effective elastic wave signal generated by the driver touching the steering wheel, reducing misjudgment caused by noise interference or false triggering, identifying the driver's touch behavior of the steering wheel based on the characteristics of the effective touch signal, and providing timely driving prompts, thereby improving the accuracy of detecting the driver's touch behavior of the steering wheel and further improving driving safety.

[0035] Specifically, in this embodiment, step 101 of acquiring the elastic wave signal collected by the elastic wave sensor array in the vehicle steering wheel may include: Sub-step 01: In response to detecting that the vehicle is in a non-parked state, detecting elastic wave signals of the steering wheel using an elastic wave sensor array in the steering wheel of the vehicle; Sub-step 02: Acquire the elastic wave signal collected by each elastic wave sensor in the elastic wave sensor array.

[0036] It should be noted that in the above steps of this embodiment, when the vehicle starts and enters a non-parked state (i.e., not in P gear), the vehicle controller automatically activates the elastic wave sensor array on the steering wheel and begins detecting elastic wave signals from the steering wheel. It should be noted that the vehicle controller monitors the vehicle's gear position to ensure that hands-off detection is performed only while the vehicle is in motion, avoiding false triggering of detection in the parked state. Specifically, the vehicle controller obtains gear information in real time via the vehicle's CAN bus to determine whether the vehicle is in a non-parked state (e.g., D gear, R gear, etc.).

[0037] Specifically, if the vehicle is detected to be unparked, the elastic wave sensor array is activated and elastic wave signal detection begins. Once activated, the elastic wave sensor array enters its operating state and begins real-time monitoring of elastic wave signals from the steering wheel. After the elastic wave sensor array is activated, the sensor controller in the vehicle controller acquires the elastic wave signals collected by each elastic wave sensor. These elastic wave signals are then transmitted to the sensor controller via a high-speed data line. Specifically, each sensor in the elastic wave sensor array collects elastic wave signals from the steering wheel in real time. Each elastic wave sensor uses the piezoelectric effect or the capacitive effect to sense the tiny vibration signals generated when the driver's hand touches the steering wheel.

[0038] The embodiment of the present invention ensures that steering wheel detection is performed only when the vehicle is moving by monitoring the gear status, avoiding misjudgment caused by accidental touch or other interference in the parking state. Multiple sensors fully cover the touch position of the steering wheel rim, ensuring comprehensive and real-time acquisition of touch signals on the steering wheel, providing a data basis for subsequent signal processing and hands-off detection.

[0039] Further, refer to Figure 2 , showing Figure 1 A flowchart of step 102 of a steering wheel detection method is provided. This method is substantially the same as the steering wheel detection method provided in the first embodiment of the present invention. Step 102 may include: Step 201, identifying interference frequency band noise and environmental noise in the elastic wave signal according to a preset interference frequency band and environmental noise waveform; Step 202: determining a target elastic wave sensor that has collected an elastic wave signal, and determining whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal; Step 203 : Filter the interference frequency band noise, environmental noise, and invalid elastic wave signals in the elastic wave signal to obtain a filtered steering wheel touch signal.

[0040] It should be noted that in an embodiment of the present invention, after the vehicle controller obtains the elastic wave signal collected by the elastic wave sensor array in the vehicle steering wheel, it filters out the interference frequency band noise and environmental noise in the elastic wave signal according to the preset interference frequency band and environmental noise waveform, and determines the target elastic wave sensor that collects the elastic wave signal, filters out the invalid elastic wave signal collected by the target elastic wave sensor, and finally obtains the steering wheel touch signal after frequency domain filtering and spatial domain filtering.

[0041] Specifically, after the sensor controller in the vehicle controller receives the elastic wave signal transmitted by the sensor array, it can perform frequency domain filtering to remove the interference frequency band noise and environmental noise in the signal. The interference frequency band noise includes low-frequency signals and high-frequency signals in a preset frequency band. The frequency domain filtering identifies the interference frequency band noise and environmental noise in the elastic wave signal through the preset interference frequency band and environmental noise waveform library.

[0042] It should be noted that this embodiment presets a low-frequency interference band (such as <50Hz, which may be generated by engine vibration) and a high-frequency interference band (such as >1kHz, which may be high-frequency electromagnetic interference), and uses a bandpass filter to filter out noise signals in these bands. The environmental noise waveform is a pre-collected noise waveform under scenarios such as in-car music, bumpy road vibration, and in-car human voices, and a noise waveform library is established. Through waveform matching, the environmental noise signals in the elastic wave signal that match the noise waveform library are identified and filtered out. In this embodiment, the elastic wave signal after interference band filtering and environmental noise filtering reduces misjudgment caused by noise interference, improves the purity of the elastic wave signal, and improves the accuracy of steering wheel detection.

[0043] In this embodiment, the sensor controller in the vehicle controller performs spatial filtering on the elastic wave signal, and determines whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal by the number of target elastic wave sensors that collect the elastic wave signal and the reflected touch position. If it is determined that the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal, the invalid elastic wave signal is filtered out. The invalid elastic wave signal includes interfering elastic wave signals and elastic wave signals of non-driver hands touching the steering wheel.

[0044] Specifically, a preset acquisition time period (e.g., 100ms) can be set, and the number of target elastic wave sensors that have acquired elastic wave signals within this time period can be determined. Due to the multi-sensor design based on the elastic wave sensor array in this embodiment, under normal touch conditions, multiple elastic wave sensors must acquire touch signals within a certain delay. If only a single sensor detects a signal and no adjacent sensors respond, the signal is determined to be an invalid elastic wave signal. Such invalid signals are directly filtered out and do not participate in subsequent signal processing. Therefore, if the number of target elastic wave sensors is determined to be one, the elastic wave signal acquired by the target elastic wave sensor is an invalid elastic wave signal. If the number of target elastic wave sensors is determined to be greater than one, the elastic wave signal acquired by the target elastic wave sensor can be determined based on the target elastic wave sensor's actual position coordinates and the acquisition signal delay to determine whether the elastic wave signal meets normal touch conditions. If it does not meet normal touch conditions, the elastic wave signal acquired by the target elastic wave sensor is an invalid elastic wave signal.

[0045] In this embodiment, interference frequency band noise, environmental noise, and invalid elastic wave signals in the elastic wave signal are filtered to obtain a final filtered steering wheel touch signal, providing high-quality data input for subsequent touch feature extraction and behavior recognition.

[0046] The embodiment of the present invention effectively eliminates noise and invalid signals caused by false triggering of a single sensor or external interference by filtering out interference frequency band noise, environmental noise and invalid elastic wave signals. The filtered steering wheel touch signal effectively reduces the interference of noise and invalid signals, thereby reducing misjudgment caused by noise interference or false triggering, and improving the accuracy of steering wheel detection.

[0047] Specifically, in this embodiment, step 202 determines the target elastic wave sensor that has collected the elastic wave signal, and determines whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal, which may specifically include: Sub-step 01: determining the number of target elastic wave sensors that have collected elastic wave signals; Sub-step 02: If the number of the target elastic wave sensor is one, determine that the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal.

[0048] It should be noted that under normal touch conditions, elastic wave signals are collected by at least multiple elastic wave sensors. Therefore, within a preset collection time period (such as 100ms), the vehicle controller records the elastic wave signals collected by all elastic wave sensors in the elastic wave sensor array, determines the number of target elastic wave sensors that collect elastic wave signals, and judges whether the number is single. If only one target elastic wave sensor collects the elastic wave signal, the elastic wave signal collected by the target elastic wave sensor is determined to be an invalid elastic wave signal, which may be noise or a false trigger signal, and the invalid elastic wave signal in the elastic wave signal needs to be filtered out.

[0049] The embodiments of the present invention effectively eliminate invalid signals caused by single sensor false triggering or external interference by filtering out invalid signals, thereby reducing the misjudgment rate. The multi-sensor redundant design ensures the reliability of signal acquisition and avoids the problem of single sensor false triggering or inaccurate signal acquisition.

[0050] Specifically, after determining the number of target elastic wave sensors that have collected elastic wave signals, step 202 may further include: Sub-step 03, if the number of target elastic wave sensors is greater than one, obtaining the position coordinates and signal acquisition time of the target elastic wave sensors; Sub-step 04, calculating the acquisition delay of the elastic wave signal acquired by the target elastic wave sensor according to the signal acquisition time; Sub-step 05: judging whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal based on the position coordinates and the collection delay.

[0051] It should be noted that in the above steps of this embodiment, after determining the number of target elastic wave sensors that have collected elastic wave signals, if the number of target elastic wave sensors is greater than one, a further determination is made as to whether the touch position satisfies a normal touch condition. Specifically, in a normal touch condition, multiple elastic wave sensors must collect touch signals within a certain delay. The position coordinates and signal acquisition time of the target elastic wave sensor are obtained, and the acquisition delay for the target elastic wave sensor to collect the elastic wave signal is calculated based on the signal acquisition time. Based on the position coordinates and acquisition delay, a determination is made as to whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal.

[0052] Specifically, the target elastic wave sensor's location coordinates and signal acquisition time are obtained. Since the target elastic wave sensor's acquisition time is recorded using a high-precision timer (e.g., a microsecond-level timer), the acquisition delay for the target elastic wave sensor to acquire the elastic wave signal is calculated based on the signal acquisition time. The acquisition delay is the difference in the target elastic wave sensor's signal acquisition times. After obtaining the acquisition delay, it is determined whether the acquisition delay is less than a preset delay threshold. Because elastic wave signals have a certain propagation speed, they arrive at different elastic wave sensors at different times. In a normal touch, the elastic wave signals arrive at the elastic wave sensors at a concentrated time. If the delay between the acquisition delays is too long, it indicates that the touch is not the same. The preset delay threshold is set based on normal touch conditions and is not specifically defined here. Therefore, if the acquisition delay is less than the preset delay threshold, the touch location can be determined based on the target elastic wave sensor's location coordinates. Based on the touch location, it can be determined whether the elastic wave signal acquired by the target elastic wave sensor is an invalid elastic wave signal that is not caused by the driver's hand touching the steering wheel.

[0053] For example, based on the propagation speed of the elastic wave signal and the actual position coordinates of the target elastic wave sensor that collected the elastic wave signal, the time delay difference between the elastic wave signals collected by multiple target elastic wave sensors can be calculated, thereby obtaining the touch position of the driver touching the steering wheel. Taking two target elastic wave sensors as an example, assuming that the position coordinates of target elastic wave sensor A and target elastic wave sensor B are ( , ) and( , ), the acquisition delay of the elastic wave signal reaching the target elastic wave sensor A and the target elastic wave sensor B is Δt, and the propagation speed of the elastic wave signal is V. Then, when the acquisition delay is less than the preset delay threshold, the position (x, y) of the touch point is calculated based on the position coordinates and the acquisition delay. In actual scenarios, the driver touching the steering wheel can generate multiple touch points. Based on the position of the touch point, the shape of the external force touching the steering wheel is judged, and it is identified whether the steering wheel is held by the hand or covered by other objects, thereby determining the elastic wave signal of the non-driver's hand holding or touching the steering wheel as an invalid elastic wave signal. The position coordinates (x, y) of the touch point where the driver touches the steering wheel are calculated by the following set of equations:

[0054] Where (x, y) is the coordinate of the touch point where the driver touches the steering wheel, ( , ) 、 ( , ) are the position coordinates of target elastic wave sensor A and target elastic wave sensor B, V is the propagation velocity of the elastic wave signal, and Δt is the acquisition delay of target elastic wave sensor A and target elastic wave sensor B.

[0055] It should be noted that, for example, when the acquisition delay of multiple elastic wave sensors touched by a driver's hands gripping the steering wheel is determined to be less than a preset threshold, the shape of the external force touching the steering wheel can be identified based on the position distribution of the elastic wave sensors. This can determine whether the driver is gripping the steering wheel or covering the steering wheel with another object, thereby determining that the elastic wave signal from a person other than the driver gripping or touching the steering wheel is invalid. For example, if the touch position is in an unconventional touch area, the signal is determined to be invalid. The conventional touch area is determined based on driving data and driving habit recognition and is not specifically limited here.

[0056] The embodiment of the present invention determines the touch position of the steering wheel based on the position coordinates and signal acquisition delay of the elastic wave sensor, effectively eliminates invalid signals caused by abnormal touch or external interference, reduces the misjudgment rate, and improves the accuracy of steering wheel hands-off detection.

[0057] Specifically, in some embodiments, step 103 performs feature extraction on the steering wheel touch signal to obtain touch features. The touch features include a touch signal peak value, a touch duration, and a touch signal frequency band, and may include: Sub-step 01: Extract the spectrum features of the steering wheel touch signal to obtain the touch signal peak and touch signal frequency band; Sub-step 02: Extract time domain features of the steering wheel touch signal, determine the duration of the steering wheel touch signal, and obtain the touch duration.

[0058] It should be noted that in the above steps of this embodiment, after obtaining the filtered steering wheel touch signal, the signal is first subjected to spectral feature extraction to obtain the peak and frequency band information of the touch signal. Spectral feature extraction can be achieved through fast Fourier transform (FFT). FFT processing is performed on the steering wheel touch signal to convert the time domain signal into a frequency domain signal, obtaining a spectrum diagram of the signal. The frequency point with the highest energy is identified in the spectrum diagram, i.e., the peak frequency of the touch signal. The peak frequency reflects the main energy distribution of the touch signal. Based on the spectrum diagram, the main frequency band range of the touch signal is determined. The frequency band range reflects the frequency distribution characteristics of the touch signal, thereby obtaining the frequency distribution and energy distribution of the steering wheel touch signal.

[0059] At the same time, time domain feature extraction is performed on the steering wheel touch signal to determine the duration of the signal, that is, the touch duration. Time domain feature extraction is achieved through signal strength threshold and time window analysis. Specifically, a time window (such as 100ms) can be set to analyze the duration of the signal. By scanning the time window, the time period when the signal strength exceeds the strength threshold is determined, and the duration of the touch signal is determined to obtain the touch duration. The touch duration reflects the duration of the touch behavior.

[0060] The embodiment of the present invention processes the touch signal from two dimensions, frequency and time, through spectrum feature extraction and time domain feature extraction, effectively analyzes the frequency distribution and energy distribution of the signal, and determines the duration of the signal to identify the driver's touch behavior on the steering wheel.

[0061] Further, refer to Figure 3 , showing Figure 1 A flowchart of step 104 of a steering wheel detection method is provided. This method is substantially the same as the steering wheel detection method provided in the first embodiment of the present invention. Step 104 may include: Step 301: If the touch signal peak value, touch duration, and touch signal frequency band are less than a preset light touch threshold, it is determined that the driver's touch behavior on the steering wheel is hands-free driving; Step 302: If the touch signal peak value, touch duration, and touch signal frequency band are greater than or equal to a preset light touch threshold and less than a preset rigidity control threshold, then it is determined that the driver's touch behavior on the steering wheel is a light touch on the steering wheel; Step 303 : If the touch signal peak value, touch duration, and touch signal frequency band are greater than or equal to the preset rigid control threshold, it is determined that the driver's touch behavior on the steering wheel is a rigid control steering wheel.

[0062] It should be noted that in an embodiment of the present invention, based on the touch characteristics of the extracted touch signal, namely the touch signal peak value, touch duration and touch signal frequency band, the touch signal peak value, touch duration and touch signal frequency band are compared with the preset behavior threshold array to determine whether the touch behavior is at least one of rigid control of the steering wheel, light touch of the steering wheel and hands-free driving.

[0063] In actual driving, the driver's touch behavior on the steering wheel mainly includes gripping the steering wheel tightly, that is, grasping it firmly with both hands, or steering vigorously, that is, applying greater force to operate the steering wheel. Such touch behavior is classified as rigid control of the steering wheel, that is, applying stable and forceful control of the steering wheel; while the driver's hand touching the steering wheel is classified as light touch of the steering wheel. In addition, it also includes the driver driving hands-free, that is, not touching the steering wheel. Therefore, touch behavior includes at least one of rigid control of the steering wheel, light touch of the steering wheel, and hands-free driving. Based on historical driving data of touch behavior, a preset behavior threshold array is set. The preset behavior threshold array includes a preset light touch threshold and a preset rigid control threshold. The threshold includes a threshold range of a touch signal peak, a touch duration, and a touch signal frequency band. Among them, the preset light touch threshold is used to distinguish between light touch of the steering wheel and hands-free driving behavior, and the preset rigid control threshold is used to distinguish between light touch of the steering wheel and rigid control of the steering wheel behavior. The specific thresholds are not specifically limited here.

[0064] In this embodiment, if the touch signal peak value, touch duration and touch signal frequency band are all less than the light touch threshold, it is determined to be hands-free driving. The hands-free driving behavior is usually manifested as weak signal strength, touch duration of 0 and low signal frequency; if the touch signal peak value, touch duration and touch signal frequency band are greater than or equal to the light touch threshold and less than the rigid control threshold, it is determined to be a light touch on the steering wheel. The light touch on the steering wheel behavior is usually manifested as moderate signal strength, short duration and moderate frequency; if the touch signal peak value, touch duration and touch signal frequency band are all greater than or equal to the rigid control threshold, it is determined to be a rigid control steering wheel. The rigid control steering wheel behavior is usually manifested as strong signal strength, long duration and high frequency.

[0065] The embodiment of the present invention accurately identifies hands-off driving, lightly touching the steering wheel, and rigidly controlling the steering wheel through multi-dimensional feature comparison of touch signal peak value, touch duration, and touch signal frequency band, thereby improving the accuracy of touch behavior recognition, accurately identifying the driver's touch behavior, and promptly detecting hands-off driving behavior.

[0066] Reference Figure 4 , shows a schematic structural diagram of a steering wheel detection device provided by an embodiment of the present invention, the device comprising: A signal acquisition module 401 is configured to acquire elastic wave signals collected by an elastic wave sensor array in a vehicle steering wheel; wherein the elastic wave sensor array includes a plurality of elastic wave sensors uniformly disposed on a steering wheel rim; Signal filtering processing 402 is used to filter the elastic wave signal based on a preset interference frequency band and environmental noise waveform, and to determine the target elastic wave sensor that collected the elastic wave signal, to obtain a filtered steering wheel touch signal; A feature extraction module 403 is configured to extract features from the steering wheel touch signal to obtain touch features, wherein the touch features include a touch signal peak value, a touch duration, and a touch signal frequency band; a behavior recognition module 404 for performing touch behavior recognition based on the touch signal peak value, the touch duration, and the touch signal frequency band to determine the driver's touch behavior on the steering wheel; the touch behavior includes at least one of rigid steering wheel control, light steering wheel touch, and hands-free driving; The prompt generation module 405 is configured to generate driving prompt information according to the touch behavior and use the driving prompt information for prompting.

[0067] Furthermore, the signal acquisition module 401 includes: a detection submodule, configured to detect elastic wave signals from a steering wheel using an elastic wave sensor array in the steering wheel of the vehicle in response to detecting that the vehicle is in an unparked state; The acquisition submodule is used to acquire the elastic wave signal collected by each elastic wave sensor in the elastic wave sensor array.

[0068] Furthermore, the signal filtering process 402 includes: A first identification submodule is configured to identify interference frequency band noise and environmental noise in the elastic wave signal according to a preset interference frequency band and environmental noise waveform; a second identification submodule, configured to determine a target elastic wave sensor that has collected the elastic wave signal, and to judge whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal; The filtering submodule is used to filter out interference frequency band noise, environmental noise and invalid elastic wave signals in the elastic wave signal to obtain a filtered steering wheel touch signal.

[0069] Furthermore, the second identification submodule includes: a first determining unit, configured to determine the number of target elastic wave sensors that have collected the elastic wave signal; The second determining unit is configured to determine that the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal if the number of the target elastic wave sensor is one.

[0070] Furthermore, the second identification submodule further includes: an acquiring unit, configured to acquire the position coordinates and signal acquisition time of the target elastic wave sensor if the number of the target elastic wave sensor is greater than one; a calculation unit, configured to calculate an acquisition delay of the elastic wave signal acquired by the target elastic wave sensor according to the signal acquisition time; A judging unit is configured to judge whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal based on the position coordinates and the collection delay.

[0071] Furthermore, the feature extraction module 403 includes: A first extraction submodule is configured to extract spectrum features of the steering wheel touch signal to obtain a touch signal peak value and a touch signal frequency band; The second extraction submodule is configured to perform time domain feature extraction on the steering wheel touch signal, determine the duration of the steering wheel touch signal, and obtain the touch duration.

[0072] Furthermore, the behavior recognition module 404 includes: a first identification submodule, configured to determine that the driver's touch behavior on the steering wheel is hands-free driving if the touch signal peak value, the touch duration, and the touch signal frequency band are less than a preset light touch threshold; a second identification submodule, configured to determine that the driver's touch behavior on the steering wheel is a light touch on the steering wheel if the touch signal peak value, the touch duration, and the touch signal frequency band are greater than or equal to a preset light touch threshold and less than a preset rigidity control threshold; The third identification submodule is configured to determine that the driver's touch behavior on the steering wheel is a rigid control steering wheel if the touch signal peak value, the touch duration, and the touch signal frequency band are greater than or equal to the preset rigid control threshold.

[0073] The steering wheel detection device provided by an embodiment of the present invention obtains the elastic wave signal collected by the elastic wave sensor array in the vehicle steering wheel. The elastic wave sensor array includes multiple elastic wave sensors evenly deployed on the steering wheel rim. According to the preset interference frequency band and environmental noise waveform, and the target elastic wave sensor that collects the elastic wave signal is determined, the elastic wave signal is filtered to obtain a filtered steering wheel touch signal, and the steering wheel touch signal is feature extracted to obtain a touch feature. The touch behavior is identified according to the touch signal peak, touch duration and touch signal frequency band, the driver's touch behavior of the steering wheel is determined, driving prompt information is generated according to the touch behavior, and the driving prompt information is used for prompting. The embodiment of the present invention captures the elastic wave signal on the steering wheel by deploying an elastic wave sensor array on the steering wheel, thereby solving the defect that traditional pressure sensors cannot detect weak touch, improving the recognition rate and detection accuracy of hand false touch, filtering the elastic wave signal based on the interference frequency band, environmental noise and specific sensors, effectively eliminating noise or external interference and invalid signals generated by sensor false triggering, and obtaining the effective elastic wave signal generated by the driver touching the steering wheel, reducing misjudgment caused by noise interference or false triggering, identifying the driver's touch behavior of the steering wheel based on the characteristics of the effective touch signal, and providing timely driving prompts, thereby improving the accuracy of detecting the driver's touch behavior of the steering wheel and further improving driving safety.

[0074] Reference Figure 5 , an embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, it includes a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504; Processor 501; a memory 503 for storing processor-executable instructions; The processor 501 is configured to execute the instructions to implement the steering wheel detection method as described above.

[0075] The communication bus mentioned in the terminal above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0076] The communication interface is used for communication between the above terminal and other devices.

[0077] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0078] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0079] In another embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steering wheel detection method described in any one of the above embodiments is implemented.

[0080] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in accordance with the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state disk (SSD)).

[0081] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0082] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A steering wheel detection method, characterized in that: The method comprises: Acquiring an elastic wave signal collected by an elastic wave sensor array in a vehicle steering wheel; wherein the elastic wave sensor array includes a plurality of elastic wave sensors uniformly disposed on a steering wheel rim; According to a preset interference frequency band and an ambient noise waveform, and determining a target elastic wave sensor that has collected the elastic wave signal, filtering the elastic wave signal to obtain a filtered steering wheel touch signal; Extracting features from the steering wheel touch signal to obtain touch features, wherein the touch features include a touch signal peak value, a touch duration, and a touch signal frequency band; performing touch behavior recognition based on the touch signal peak value, the touch duration, and the touch signal frequency band to determine the driver's touch behavior on the steering wheel; wherein the touch behavior includes at least one of rigidly controlling the steering wheel, lightly touching the steering wheel, and hands-free driving; Driving prompt information is generated according to the touch behavior, and the driving prompt information is used for prompting.

2. The method according to claim 1, characterized in that The step of obtaining the elastic wave signal collected by the elastic wave sensor array in the vehicle steering wheel includes: In response to detecting that the vehicle is in an unparked state, an elastic wave sensor array in a steering wheel of the vehicle is used to detect an elastic wave signal of the steering wheel; Acquire elastic wave signals collected by each elastic wave sensor in the elastic wave sensor array.

3. The method according to claim 1, characterized in that The filtering of the elastic wave signal according to the preset interference frequency band and the ambient noise waveform, and determining the target elastic wave sensor that collects the elastic wave signal to obtain a filtered steering wheel touch signal, includes: Identifying interference frequency band noise and environmental noise in the elastic wave signal according to a preset interference frequency band and environmental noise waveform; determining a target elastic wave sensor that has collected the elastic wave signal, and determining whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal; Interference frequency band noise, environmental noise, and invalid elastic wave signals in the elastic wave signal are filtered to obtain a filtered steering wheel touch signal.

4. The method according to claim 3, characterized in that The determining of the target elastic wave sensor that has collected the elastic wave signal and judging whether the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal includes: determining the number of target elastic wave sensors that have collected the elastic wave signal; If the number of the target elastic wave sensor is one, it is determined that the elastic wave signal collected by the target elastic wave sensor is an invalid elastic wave signal.

5. The method according to claim 4, characterized in that After determining the number of target elastic wave sensors that have collected the elastic wave signals, the method further includes: If the number of the target elastic wave sensors is greater than one, obtaining the position coordinates and signal acquisition time of the target elastic wave sensors; Calculating the acquisition delay of the elastic wave signal acquired by the target elastic wave sensor according to the signal acquisition time; According to the position coordinates and the acquisition delay, it is determined whether the elastic wave signal acquired by the target elastic wave sensor is an invalid elastic wave signal.

6. The method according to claim 1, characterized in that The feature extraction of the steering wheel touch signal to obtain touch features, wherein the touch features include a touch signal peak value, a touch duration, and a touch signal frequency band, including: Extracting spectrum features of the steering wheel touch signal to obtain a touch signal peak and a touch signal frequency band; Perform time domain feature extraction on the steering wheel touch signal, determine the duration of the steering wheel touch signal, and obtain the touch duration.

7. The method according to claim 1, characterized in that The touch behavior recognition is performed based on the touch signal peak value, the touch duration, and the touch signal frequency band to determine the driver's touch behavior on the steering wheel; wherein the touch behavior includes at least one of rigid control of the steering wheel, light touch of the steering wheel, and hands-free driving, including: If the touch signal peak value, the touch duration, and the touch signal frequency band are less than a preset light touch threshold, it is determined that the driver's touch behavior on the steering wheel is hands-free driving; If the touch signal peak value, the touch duration, and the touch signal frequency band are greater than or equal to the preset light touch threshold and less than the preset rigidity control threshold, it is determined that the driver's touch behavior on the steering wheel is a light touch on the steering wheel; If the touch signal peak value, the touch duration, and the touch signal frequency band are greater than or equal to the preset rigid control threshold, it is determined that the driver's touch behavior on the steering wheel is a rigid control steering wheel.

8. A steering wheel detection device, characterized in that: The device comprises: A signal acquisition module, configured to acquire elastic wave signals collected by an elastic wave sensor array in a vehicle steering wheel; wherein the elastic wave sensor array comprises a plurality of elastic wave sensors uniformly disposed on a steering wheel rim; Signal filtering processing is used to filter the elastic wave signal according to a preset interference frequency band and environmental noise waveform, and to determine the target elastic wave sensor that collected the elastic wave signal, to obtain a filtered steering wheel touch signal; A feature extraction module, configured to extract features from the steering wheel touch signal to obtain touch features; wherein the touch features include a touch signal peak value, a touch duration, and a touch signal frequency band; a behavior recognition module, configured to identify touch behavior based on the touch signal peak value, the touch duration, and the touch signal frequency band, and determine the driver's touch behavior on the steering wheel; the touch behavior includes at least one of rigid steering wheel control, light steering wheel touch, and hands-free driving; A prompt generation module is used to generate driving prompt information according to the touch behavior and use the driving prompt information for prompting.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the steering wheel detection method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steering wheel detection method according to any one of claims 1 to 7 is implemented.

Images