Tire pressure monitoring method and system and storage medium

Abstract

The invention relates to the technical field of vehicle control, and discloses a tire pressure monitoring method and system and a storage medium, the method comprises the following steps: according to a road condition grade detection mode, in combination with corresponding vehicle-mounted road condition information and a road condition grade calculation rule, detecting a road condition grade; wherein the vehicle-mounted road condition information comprises first vehicle-mounted road condition information and second vehicle-mounted road condition information; the tire pressure monitoring frequency is determined according to the road condition grade, and the wireless Bluetooth tire pressure monitoring device is controlled to monitor the tire pressure according to the tire pressure monitoring frequency. The tire pressure monitoring frequency is determined according to the road condition grade, the effects of system resources and energy consumption can be further achieved, in addition, the road condition grade is not determined only through one parameter, the road condition grade of the current driving road of the vehicle is determined in combination with the parameters of various vehicles, and the efficiency of the system is improved. And thus, the accuracy of road condition grade determination is ensured.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a tire pressure monitoring method, system and storage medium. Background Art

[0002] With the rapid development of the automobile industry, driving safety has received more and more attention. As the part that directly contacts the ground during driving, the tire pressure condition has a vital impact on the vehicle's handling, stability and safety. Traditional tire pressure monitoring systems usually use a fixed monitoring frequency and cannot be flexibly adjusted according to actual road conditions, which to a certain extent limits the accuracy and timeliness of real-time monitoring of tire conditions. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a tire pressure monitoring method, system and storage medium, which can realize timely and accurate tire pressure monitoring.

[0004] In a first aspect, an embodiment of the present application provides a tire pressure monitoring method, comprising:

[0005] According to the road condition level detection method, the road condition level is detected in combination with the corresponding vehicle-mounted road condition information and the road condition level calculation rule; wherein the vehicle-mounted road condition information includes the first vehicle-mounted road condition information and the second vehicle-mounted road condition information;

[0006] The tire pressure monitoring frequency is determined according to the road condition level, and the wireless Bluetooth tire pressure monitoring device is controlled to monitor the tire pressure according to the tire pressure monitoring frequency.

[0007] In some embodiments, before determining the road condition level in accordance with the road condition level, in combination with the corresponding vehicle-mounted road condition information and the road condition level calculation rule, the method further includes:

[0008] Determining the road condition level detection method;

[0009] If the road condition level is detected in a first manner, target vehicle-mounted road condition information for detecting the road condition level in accordance with the first manner is determined; wherein the target vehicle-mounted road condition information is one or more types of information in the first vehicle-mounted road condition information; the first vehicle-mounted road condition information includes acceleration information, angular velocity information, positioning information, and a front image;

[0010] The method of detecting the road condition level in accordance with the road condition level detection method, in combination with the corresponding vehicle-mounted road condition information and the road condition level calculation rule, includes:

[0011] Calculate the road condition value corresponding to each target vehicle-mounted road condition information respectively;

[0012] The road condition level is calculated according to each road condition value in combination with the corresponding road condition level calculation rule.

[0013] In some embodiments, the calculation of the road condition value corresponding to the acceleration information includes:

[0014] An acceleration level is determined according to the vertical acceleration of the vehicle in the vertical direction in the acceleration information, and a corresponding first road condition value is determined according to the acceleration level.

[0015] In some embodiments, the calculation of the road condition value corresponding to the angular velocity information includes:

[0016] An angular velocity level is determined according to the angular velocity information, and a corresponding second road condition value is determined according to the angular velocity level.

[0017] In some embodiments, the calculation of the road condition value corresponding to the positioning information includes:

[0018] The current road condition of the vehicle is determined according to the positioning information and in combination with a map, and a third road condition value is determined according to the road condition.

[0019] In some embodiments, the calculation of the road condition value corresponding to the front image includes:

[0020] Preprocessing the front image to obtain a target front image;

[0021] Inputting the target front image into an edge detection model, a texture feature extraction model, and an object recognition model respectively to obtain the edge features, texture features, and obstacle features respectively;

[0022] According to the edge features, texture features and obstacle features, lane line information, road surface flatness information and obstacle information are respectively obtained;

[0023] A fourth road condition value is determined according to the lane line information, road surface flatness information and obstacle information.

[0024] In some embodiments, the method further includes: if the second method is used to detect the road condition level, then the method of detecting the road condition level in accordance with the road condition level detection method, combined with the corresponding vehicle-mounted road condition information and the road condition level calculation rule, includes:

[0025] The road condition level is detected according to the second vehicle-mounted road condition information in combination with a fuzzy logic algorithm, a neural network algorithm or a decision tree algorithm; wherein the second vehicle-mounted road condition information includes the vehicle vibration amplitude and the compression and rebound frequency of the suspension system.

[0026] In a second aspect, an embodiment of the present application provides a tire pressure monitoring system, wherein the vehicle includes a wireless Bluetooth tire pressure monitoring module, an on-board road condition monitoring module, a processor, and a memory;

[0027] The wireless Bluetooth tire pressure monitoring module is connected to the processor and is used to detect the tire pressure of the vehicle and transmit it to the processor;

[0028] The vehicle-mounted road condition monitoring module is connected to the processor, and acquires the vehicle-mounted road condition information of the vehicle by detecting the vehicle and sends the information to the processor;

[0029] The memory stores a computer program, and the processor is used to execute the computer program to implement the above tire pressure monitoring method.

[0030] In some embodiments, the vehicle-mounted road condition monitoring module includes an acceleration sensor, a gyroscope, a positioning module, a camera, an image processing module, and an air spring extension acceleration sensor;

[0031] The acceleration sensor is used to measure the acceleration information of the vehicle; the gyroscope is used to measure the angular velocity information of the vehicle; the positioning module is used to obtain the positioning information of the vehicle; the camera is used to capture the front image of the vehicle; the image processing module is used to process the front image; the air spring extension acceleration sensor is used to detect the compression and rebound frequency of the suspension system of the vehicle;

[0032] The wireless Bluetooth tire pressure monitoring module includes a pressure sensor and a Bluetooth communication module;

[0033] The pressure sensor is used to detect the tire pressure of the vehicle; and the Bluetooth communication module is used to transmit the tire pressure detected by the pressure sensor to the processor.

[0034] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed on a processor, implements the tire pressure monitoring method described above.

[0035] The embodiments of the present application have the following beneficial effects: the present application determines the road condition level according to the road condition level determination method required by the user through the vehicle-mounted road condition information. It can be understood that the determination of the road condition level in the present embodiment is not simply determined by only one parameter, but combines multiple vehicle parameters to determine the road condition level of the road the vehicle is currently traveling on, thereby ensuring the accuracy of the road condition level determination. In addition, the tire pressure monitoring frequency in the present embodiment is determined according to the road condition level, thereby achieving the effect of system resources and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of a tire pressure monitoring system according to an embodiment of the present application is shown;

[0038] Figure 2 A first flow chart of a tire pressure monitoring method according to an embodiment of the present application is shown;

[0039] Figure 3 A second flow chart of the tire pressure monitoring method according to an embodiment of the present application is shown;

[0040] Figure 4 A structural schematic diagram of a tire pressure monitoring device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0043] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0044] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0045] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0046] In the prior art, tire pressure monitoring for vehicles is usually performed at a fixed frequency. In some poor road conditions, the tire pressure information cannot be obtained in time, which may easily lead to vehicle unsafe situations. In addition, in better road conditions, high-frequency tire pressure monitoring may easily lead to a waste of system resources.

[0047] Based on this, the present application proposes a tire pressure monitoring method, system and storage medium. The real-time road condition level can be determined according to the real-time vehicle road condition information obtained, and then the frequency of tire pressure monitoring can be determined according to the road condition level. If the road condition is poor, the frequency of tire pressure monitoring can be higher. If the road condition is good, the frequency of tire pressure monitoring can be lower.

[0048] First, the tire pressure monitoring system in the vehicle is explained.

[0049] like Figure 1As shown, the tire pressure monitoring system includes a wireless Bluetooth tire pressure monitoring module 10, a vehicle road condition monitoring module 20, a processor 30 and a memory 40. Among them, the wireless Bluetooth tire pressure monitoring module 10 includes a pressure sensor 11 and a temperature sensor 12 installed in each tire, a microcontroller 13 and a Bluetooth communication module 14; the pressure sensor 11 is used to measure the pressure inside the tire, and the measurement accuracy can reach ±0.1bar; the temperature sensor 12 is used to measure the temperature inside the tire, and the measurement range is -40℃ to 125℃, and the accuracy is ±1℃; the microcontroller 13 is used to receive the tire pressure data and temperature data monitored by the pressure sensor 11 and the temperature sensor 12 in each tire according to the prescribed tire pressure monitoring frequency, and process and encode them; the processed and encoded tire pressure data and temperature data will be transmitted to the vehicle's processor 30 through the Bluetooth communication module 14, so that the processor 30 controls the vehicle according to the tire pressure data and temperature data. Among them, the Bluetooth communication in this embodiment can use the Bluetooth 5.0 standard protocol for wireless transmission, and the transmission distance can reach 50 meters, thereby ensuring stable data transmission. The processing and encoding of the tire pressure data collected by the pressure sensor 11 and the temperature data collected by the temperature sensor 12 are mainly for filtering and correcting the collected tire pressure data and temperature data to ensure the accuracy and reliability of the sensor data and reduce the possibility of false alarms and missed alarms; then the filtered and corrected tire pressure data and temperature data need to be converted into a standardized digital format for subsequent processing and analysis; finally, the data is encoded into a specific communication protocol so that the data can be wirelessly transmitted via Bluetooth to achieve remote monitoring and management.

[0050] The vehicle-mounted road condition monitoring module 20 includes but is not limited to an acceleration sensor 21 , a gyroscope 31 , a positioning module 32 (which may be a GPS module), a camera 33 , an image processing module 34 and an air spring extension acceleration sensor 351 .

[0051] Among them, the acceleration sensor 21 can be used to measure the acceleration of the vehicle in three axes, where the three axes refer to the direction of movement of the vehicle in three-dimensional space. This usually refers to the longitudinal (forward / reverse), lateral (left and right movement) and vertical (up and down movement) directions of the vehicle. Among them, the longitudinal direction is the x-axis (the direction of the vehicle's forward and backward movement), the lateral direction is the y-axis (the direction of the vehicle's left and right movement), and the vertical direction is the z-axis (the direction of the vehicle's up and down movement). The accuracy of the acceleration sensor 21 used in this embodiment is ±0.01g. The gyroscope 31 is used to measure the angular velocity and attitude change of the vehicle, that is, to measure the rotational angular velocity of the vehicle. The accuracy of the gyroscope 31 in this embodiment can be ±0.1° / s. The positioning module 32 is used to provide the real-time position and driving speed of the vehicle, and the positioning accuracy is within 5 meters. The camera 33 is used to collect images of the road in front of the vehicle, with a resolution of 1920×1080 pixels and a frame rate of 30fps. The image processing module 34 analyzes and judges the road conditions such as the flatness, slope, and curves of the road through an image recognition processing algorithm. The air spring extension acceleration sensor 35 is used to measure the compression and rebound frequencies of the vehicle's suspension system.

[0052] The processor 30 is used to receive data transmitted by the wireless Bluetooth tire pressure monitoring module 10 and the vehicle-mounted road condition monitoring module 20, and determine the road condition level based on the data transmitted by the vehicle-mounted road condition monitoring module 20. Then the processor 30 determines the tire pressure monitoring frequency based on the road condition level, and controls the wireless Bluetooth tire pressure monitoring module 10 to monitor the tire pressure of the vehicle according to the determined tire pressure monitoring frequency.

[0053] The memory stores a computer program, and the processor 30 runs the computer program to enable the vehicle to execute the functions of the various modules in the above-mentioned tire pressure monitoring method or the above-mentioned tire pressure monitoring device.

[0054] Among them, the processor 30 can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0055] The memory 40 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0056] The tire pressure monitoring method is described below in conjunction with some specific embodiments.

[0057] Figure 2 A schematic diagram of a process flow of a tire pressure monitoring method according to an embodiment of the present application is shown. Exemplarily, the tire pressure monitoring method includes the following steps:

[0058] Step S100, detecting the road condition level according to the road condition level detection method, combined with the corresponding vehicle-mounted road condition information and the road condition level calculation rule.

[0059] Among them, the vehicle-mounted road condition information includes first vehicle-mounted road condition information and second vehicle-mounted road condition information; the first vehicle-mounted road condition information includes: acceleration information, angular velocity information, positioning information and the current road front image of the vehicle, and the second vehicle-mounted road condition information includes the vehicle vibration amplitude and the compression and rebound frequency of the suspension system.

[0060] Before executing step S100, it is necessary to first determine the road condition level determination method. The road condition level determination method can be selected by the user through the vehicle display, and then the vehicle display sends the selected road condition level determination method to the processor, and the processor can monitor the tire pressure according to the road condition level determination method selected by the user.

[0061] In this embodiment, there are two main ways to determine the road condition level. The first way is to determine the road condition level through acceleration information, angular velocity information, positioning information and the image of the vehicle's current road ahead; the second way is to determine the road condition level through the vehicle's vibration amplitude and the compression and rebound frequency of the suspension system.

[0062] If the user determines to determine the road condition level through the first method, it is necessary to determine which information among the speed information, angular velocity information, positioning information, and the image of the vehicle's current road front is used to determine the road condition level. Since any one of the four information, speed information, angular velocity information, positioning information, and the image of the vehicle's current road front, can be used to determine the road condition level, but if only one information is used to determine the road condition level, the problem of inaccurate road condition level determination may occur. Therefore, in order to improve the accuracy of the road condition level determination, at least two of the four information, speed information, angular velocity information, positioning information, and the image of the vehicle's current road front, are usually selected to determine the road condition level. After determining the corresponding on-board road condition information, the road condition level calculation rules corresponding to these on-board road condition information can also be determined. Among them, for the first method, no matter which target on-board road condition information is used, the road condition level calculation rules used are all weighted summation methods, but different combinations of target on-board road condition information have different weights assigned to each target on-board road condition information.

[0063] In some implementations, if the first method is determined to be used and the target vehicle road condition information is also determined, Figure 3 As shown, step S100 includes steps S110 to S120:

[0064] Step S110, respectively calculating the road condition value corresponding to each target vehicle-mounted road condition information.

[0065] After obtaining the acceleration information of the acceleration sensor, since whether the road condition is bumpy mainly depends on whether the vehicle fluctuates up and down, the acceleration level can be determined according to the vertical acceleration of the vehicle in the vertical direction in the acceleration information, and the corresponding first road condition value can be determined according to the acceleration level.

[0066] In this embodiment, the first road condition value corresponding to each vertical acceleration range is pre-set, such as the vertical acceleration of -0.1 m / s 2 -0 m / s 2 Within range or 0m / s 2 -+0.1m / s 2 Within the range (i.e. ±0.1m / s 2 If the vertical acceleration is within +0.1m / s 2 -+0.3m / s 2 Within range or -0.3m / s 2 --0.1m / s 2 Within the range (i.e. ±0.1-±0.3m / s 2If the vertical acceleration is within +0.3m / s, it means that the vehicle is fluctuating and the current road condition is average. 2 -+0.5m / s 2 Within range or -0.5m / s 2 --0.3m / s 2 Within the range (i.e. ±0.3-±0.5m / s 2 If the vertical acceleration is within +0.5m / s 2 Above or -0.5m / s 2 When the vertical acceleration is as follows, it means that the vehicle is fluctuating violently and the current road condition is bad; each vertical acceleration range corresponds to a first road condition value, so after the vertical acceleration is determined according to the acquired acceleration information, the current first road condition value can be determined according to the acceleration range corresponding to the vertical acceleration. It can be understood that the above division of the vertical acceleration range is only exemplary, and each vertical acceleration range and the road condition value corresponding to each range can be divided according to actual needs.

[0067] Among them, the angular velocity information is obtained through the gyroscope on the vehicle, and the angular velocity information is used to indicate the change of the vehicle's yaw angular velocity. In this embodiment, in order to facilitate the determination of the road condition level, a second road condition value corresponding to each angular velocity range is preset. For example, when the angular velocity is within the range of -1 radian / second to 0 radian / second or within the range of 0 radian / second to +1 radian / second (i.e., within the range of ±1 radian / second), it means that the vehicle has no obvious turning action at this time, and the driving direction is stable, which means that the current road condition may be good; if the angular velocity is within the range of -5 radian / second to -1 radian / second or within the range of +1 radian / second to +5 radian / second (i.e., within the range of ±5 radian / second), it means that the vehicle is If the vehicle has a small yaw rate change, the current road condition may be relatively general; if the angular velocity is within the range of -10 radians / second to -5 radians / second or within the range of +5 radians / second to +10 radians / second (i.e. within the range of ±5-±10 radians / second), it means that the vehicle's yaw rate changes greatly and the current road condition is poor; if the angular velocity is less than -10 radians / second or greater than +10 radians / second (i.e. the angular velocity changes by more than ±10 radians / second), it means that the vehicle's yaw rate changes dramatically, which means that the current road condition may be relatively bad. It can be understood that the above division of the angular velocity range is only exemplary, and each angular velocity range and the road condition value corresponding to each range can be divided according to actual needs.

[0068] Among them, the positioning information is the location information of the current vehicle fed back by the positioning module, and the positioning module can be a GPS module or a Beidou module. According to the current location information of the vehicle fed back by the positioning module, the type of the road on which the vehicle is currently traveling can be determined in combination with the map, and the third road condition value corresponding to the positioning information can be determined according to the road type. In this embodiment, in order to facilitate the determination of the road condition level, the third road condition value corresponding to the road type determined by the positioning information is preset. If the vehicle is currently traveling on a highway or a newly built urban trunk road according to the positioning information and combined with the map, the current road condition can be determined to be good through the positioning information; if the vehicle is currently traveling on an ordinary urban road or a road with a certain amount of traffic according to the positioning information and combined with the map, the current road condition can be determined to be general through the positioning information; if the vehicle is currently traveling on a rural dirt road or a road under repair according to the positioning information and combined with the map, the current road condition can be determined to be poor through the positioning information; if the vehicle is currently traveling on an extreme road such as a mudslide, a flooded road, or a serious landslide according to the positioning information and combined with the map, the current road condition can be determined to be bad through the positioning information. It can be understood that the above determination of roads and road condition information based on positioning information is only exemplary, and the road condition value corresponding to each road type can be determined according to actual needs.

[0069] For image information, in this embodiment, an image in front of the vehicle is obtained by a camera, and the image is processed to obtain edge features, texture features and obstacle features of the image, and lane line information, road surface flatness information and obstacle information are respectively obtained based on these edge features, texture features and obstacle features. After the lane line information, road surface flatness information and obstacle information are obtained, the fourth road condition value is determined based on the preset mapping relationship between the lane line information, road surface flatness information and obstacle information and the fourth road condition value. Among them, the mapping relationship between the lane line information, road surface flatness information and obstacle information and the fourth road condition value is that the lane line information, road surface flatness information and obstacle information are obtained by processing the image information, and each combination of lane line information, road surface flatness information and obstacle information corresponds to a fourth road condition value.

[0070] Exemplarily, the image processing includes image preprocessing and feature extraction. The image preprocessing process includes:

[0071] Grayscale the image: The image obtained by the camera is usually a color image (RGB format), containing a large amount of color information. In order to simplify the subsequent processing and reduce the amount of calculation, grayscale processing is first performed, and then the color image is converted into a grayscale image. Each pixel is represented by only one grayscale value.

[0072] Filtering and denoising: In the actual road environment, the image may be disturbed by various noises, such as sensor noise, salt and pepper noise caused by light changes, etc. Median filtering or Gaussian filtering can be used to remove noise; among them, median filtering replaces the gray value of the pixel with the median of the gray value of the pixel neighborhood, which is better for removing salt and pepper noise; Gaussian filtering calculates the weighted average of the pixel neighborhood based on the Gaussian function, which is more effective for removing Gaussian noise. For example, for a median filter window, it will sort the gray values ​​of the 9 pixels in the window, and then take the middle value as the new gray value of the center pixel.

[0073] Image enhancement: To make the road features in the image more obvious, image enhancement can be performed. Histogram equalization is a commonly used method that adjusts the image histogram to make the grayscale distribution of the image more uniform, thereby enhancing the contrast of the image. For example, for a road image with a narrow grayscale range, after histogram equalization, the contrast between the originally darker road surface and the brighter traffic signs and other details will increase, which is more conducive to subsequent recognition.

[0074] After the image is preprocessed, feature extraction is performed using the preprocessed image.

[0075] The feature extraction process includes:

[0076] Edge detection: Edge information in road images is very important for judging road conditions, such as lane line edges, edges between roads and roadside obstacles, etc. The Canny edge detection algorithm can be used, which includes four steps: Gaussian filtering, calculating gradient amplitude and direction, non-maximum suppression, and double threshold detection. First, Gaussian filtering is used to remove noise, then the gradient amplitude and direction of each pixel are calculated, and then non-maximum suppression is performed to retain only the local maximum value in the gradient direction as the edge point. Finally, double threshold detection is used to connect the edges and remove some false edges. For example, when detecting the edge of a lane line, Canny edge detection can accurately extract the outline of the lane line, providing a basis for subsequent lane line recognition.

[0077] Texture feature extraction: The texture features of the road surface can reflect the road conditions. For example, the texture of a smooth road surface is relatively regular, while the texture of a road surface with potholes or damage will show irregular changes. The gray level co-occurrence matrix (GLCM) can be used to extract texture features. GLCM is a second-order statistic that describes the joint distribution of gray levels of two pixels separated by a certain distance and direction in an image; the texture features are characterized by calculating the energy, contrast, correlation and other parameters of GLCM. For example, for a good road surface with uniform texture, the contrast of its gray level co-occurrence matrix is ​​low, while for a road surface with potholes, the contrast will be higher.

[0078] Object recognition feature extraction: Identifying obstacles, vehicles and other objects on the road is also critical for judging road conditions. The shape features (such as aspect ratio, circularity, etc.), color features (before grayscale conversion) and HOG (Histogram of Oriented Gradients) features of the object can be extracted. The HOG feature is a feature descriptor used for target detection. It constructs features by calculating and counting the gradient direction histogram of the local area of ​​the image. For example, when detecting vehicles on the road, the HOG feature can effectively describe the contour and shape features of the vehicle. Combined with classifiers such as support vector machines (SVM), it can determine whether there is a vehicle and the location of the vehicle.

[0079] After the feature extraction process is completed, that is, after the features in the image are extracted, the road condition is judged based on the extracted features.

[0080] Identify lane lines through extracted edge features: Based on the extracted edge features, use methods such as Hough transform to identify lane lines. Hough transform can convert the straight line detection problem in image space into parameter space for solution. For example, find peaks that meet certain conditions in parameter space, and the parameters corresponding to these peaks are the parameters of the straight line (lane line) in the image, such as slope and intercept. By identifying the integrity, clarity and curvature of the lane line, the level of the lane line can be determined. If the lane line is clear, continuous and has normal curvature, it means that the road condition is good; if the lane line is blurred, intermittent or has abnormal curvature, it may mean that the road condition is poor.

[0081] Identify road conditions through extracted texture features: The road surface flatness level can be determined based on the texture features. If the road surface texture is relatively regular, it means that the road condition is good. If the road surface texture features are very irregular and the contrast is high, it means that the road condition is poor.

[0082] Identify obstacles through extracted object recognition features: Use the extracted object features combined with a classifier (such as a convolutional neural network in deep learning, or a traditional feature-based classifier) ​​to identify obstacles on the road. For example, the extracted object shape, color, and texture features are input into a trained classifier to determine whether it is an obstacle such as a stone or a branch. If multiple obstacles are identified, and the obstacles are densely distributed or large in size, affecting the normal passage of vehicles, then the road condition can be determined to be poor or severe.

[0083] After acquiring the lane line information, road surface roughness information and obstacle information as described above, the integrated information of the lane line information, road surface roughness information and obstacle information is obtained. The fourth road condition value corresponding to the current image can be obtained according to the correspondence between the integrated information and the fourth road condition value.

[0084] In another embodiment, after the feature extraction process is completed, when judging the road condition level based on the extracted features, a deep learning model can be used for judgment. The deep learning model used can be AlexNet. After acquiring the features of the image captured by the camera, the acquired features are input into the AlexNet model, and the road condition level is output through the AlexNet model. The AlexNet can be trained using historical road condition data during training.

[0085] Step S120, calculating the road condition grade according to each road condition value in combination with the corresponding road condition grade calculation rule.

[0086] After determining the target vehicle-mounted road condition information used for determining the road condition level, the road condition value corresponding to each target vehicle-mounted road condition information is calculated according to the above method, and finally the road condition level is determined according to the road condition level calculation rules corresponding to these target vehicle-mounted road condition information. In this embodiment, the road condition level is determined by weighted summation, and the weight corresponding to each type of target vehicle-mounted road condition information is pre-set. For example, if the target vehicle-mounted road condition information includes acceleration information, angular velocity information, and positioning information, the weight corresponding to each target vehicle-mounted road condition information can be 0.6, 0.2, and 0.2; if the target vehicle-mounted road condition information includes acceleration information, angular velocity information, positioning information, and a front image, the weight corresponding to each target vehicle-mounted road condition information can be 0.5, 0.2, 0.1, and 0.2; if the target vehicle-mounted road condition information includes acceleration information and angular velocity information, the weight corresponding to each target vehicle-mounted road condition information can be 0.6, 0.4, etc. It can be understood that the above setting of the weight of the target vehicle road condition information is only exemplary and is not limited to this embodiment in specific use. The specific weight can be set according to actual needs.

[0087] In some embodiments, if the second method is used to determine the road condition level, the road condition level is determined according to the road condition level determination method in combination with the corresponding on-board road condition information and road condition level calculation rules, including: determining the road condition level based on the vehicle vibration amplitude and the compression and rebound frequency of the suspension system in combination with a fuzzy logic algorithm, a neural network algorithm, or a decision tree algorithm.

[0088] Exemplarily, the vibration amplitude of the vehicle can be determined based on the vertical acceleration information; the compression and rebound frequencies of the suspension system can be determined based on the information collected by the air spring extension acceleration sensor.

[0089] After obtaining the vehicle vibration amplitude and the compression and rebound frequencies of the suspension system, the road condition level can be determined in the following ways.

[0090] Fuzzy logic algorithms can be used to determine the road condition level. First, the vehicle vibration amplitude, compression and rebound frequency of the suspension system are fuzzy processed. For example, the vehicle vibration amplitude is divided into three fuzzy sets of "small", "medium" and "large". This can be achieved by setting thresholds. For example, a vibration amplitude less than 2mm is defined as "small", 2-5mm is defined as "medium", and greater than 5mm is defined as "large". Similarly, the compression and rebound frequencies of the suspension system are also divided into fuzzy sets such as "low", "medium" and "high".

[0091] Fuzzy rule establishment: Fuzzy rules are established based on experience and experimental data. For example, if the vehicle vibration amplitude is "small" and the suspension system compression and rebound frequency is "low", the road condition level is "good"; if the vehicle vibration amplitude is "medium" and the suspension system compression and rebound frequency is "medium", the road condition level is "average"; if the vehicle vibration amplitude is "large" and the suspension system compression and rebound frequency is "high", the road condition level is "poor".

[0092] Defuzzification: The fuzzy output is converted into an accurate road condition grade through methods such as the centroid method. For example, after fuzzy reasoning, the membership of the road condition grade is obtained as "good" 0.3, "fair" 0.5, and "poor" 0.2, and the final road condition grade is calculated according to the centroid method.

[0093] In addition, a neural network algorithm may be used to determine the road condition level.

[0094] Data preprocessing: Normalize the vehicle vibration amplitude and suspension system data, that is, convert the vehicle vibration amplitude, suspension system data, etc. to the range of 0-1.

[0095] Neural network architecture: Build a multi-layer perceptron (MLP) neural network, for example, including an input layer, two hidden layers and an output layer. The input layer nodes receive normalized vehicle vibration amplitude, suspension system data, etc.; the hidden layer nodes perform nonlinear transformation on the input data through activation functions (such as ReLU functions); the output layer outputs the road condition level, for example, 0 represents "good", 1 represents "average", and 2 represents "poor".

[0096] The training process of the neural network used: a large amount of historical data with well-labeled road condition levels is used to train the neural network. The weights of the neural network are adjusted through the back-propagation algorithm to minimize the error between the road condition level output by the network and the actual labeled road condition level.

[0097] In addition, a decision tree algorithm can also be used to determine the road condition level.

[0098] Construct a decision tree: Take the vibration amplitude of the vehicle as the root node. For example, if the vibration amplitude is less than 2mm, enter the "good road condition" branch; if the vibration amplitude is greater than or equal to 2mm, the compression and rebound frequency of the suspension system is the next node. If the compression and rebound frequency of the suspension system is less than a certain value, enter the "normal road condition" branch; otherwise, enter the "bad road condition" branch.

[0099] Evaluate the decision tree: Use the test data set to evaluate the accuracy of the decision tree and calculate indicators such as accuracy and recall. If the accuracy is not high enough, you can optimize the decision tree by adjusting parameters such as the depth of the decision tree and the threshold for splitting nodes.

[0100] Step S200, determining the tire pressure monitoring frequency according to the road condition level, and controlling the wireless Bluetooth tire pressure monitoring device to monitor the tire pressure according to the tire pressure monitoring frequency.

[0101] After the road condition level is obtained in the above manner, the tire pressure monitoring frequency is determined based on the correspondence between the road condition level and the tire pressure monitoring frequency and the current road condition level. For example, when the road condition level is "good", the tire pressure monitoring frequency can be set to a lower value, such as monitoring once every 30 minutes. This is because under good road conditions, the tires are less impacted and the tire pressure changes relatively slowly. When the road condition level is "general", the tire pressure monitoring frequency is increased to once every 15 minutes. Due to slightly poor road conditions, the tires may experience faster changes in tire pressure due to some small bumps. When the road condition level is "poor", the tire pressure monitoring frequency is set to once every 5 minutes. Under poor road conditions, tires are frequently impacted, and tire pressure is prone to abnormal changes, requiring more frequent monitoring. It can be understood that the above correspondence between road condition levels and tire pressure monitoring frequencies is only exemplary and is not intended to be a limitation of this embodiment. The specific correspondence between tire pressure monitoring frequency and road condition level can be set according to actual needs. The general principle is that the worse the road conditions, the more frequent the tire pressure monitoring frequency; the better the road conditions, the less frequent the tire pressure monitoring frequency.

[0102] In some implementations, when abnormal tire pressure is detected, a warning message is issued to allow the driver to know the abnormal tire pressure information in a timely manner.

[0103] In this embodiment, the road condition level is determined according to the road condition level determination method required by the user through acceleration information, angular velocity information, positioning information, the image of the vehicle's current road ahead, the vehicle vibration amplitude, and the compression and rebound frequency of the suspension system. It can be understood that the determination of the road condition level in this embodiment is not simply determined by only one parameter, but combines multiple vehicle parameters to determine the road condition level of the vehicle's current driving road, thereby ensuring the accuracy of the road condition level determination. In addition, the tire pressure monitoring frequency in this embodiment is determined according to the road condition level, thereby achieving the effect of system resources and energy consumption, that is, under good road conditions, the tire pressure monitoring frequency is appropriately slowed down, which significantly reduces the data transmission volume of wireless communication and the system's computing and processing burden, thereby reducing the energy consumption of the entire vehicle system, extending the battery life of the sensor, and also reducing the working pressure of the vehicle-mounted electronic system. In this embodiment, the road condition level is determined by using a variety of parameters, and these parameters can be selected by the user. In this way, the user can select the corresponding road condition level determination method when driving on the corresponding road according to driving experience, and select the appropriate target vehicle-mounted road condition information when using the first method, so that the vehicle can adapt to a variety of driving environments, that is, whether it is a congested urban road, a highway, a mountain road or a road under extreme weather conditions, the tire pressure monitoring method of the present application can adaptively provide appropriate tire pressure monitoring services to ensure the driving safety of the vehicle in various complex environments. For example, on roads covered with ice and snow in winter or high-temperature roads in summer, the present application can timely adjust the tire pressure monitoring strategy according to the changes in road conditions to ensure that the tire is always in a safe state, thereby improving driving safety. In addition, by adjusting the tire pressure monitoring frequency in real time and accurately according to the road conditions, the present embodiment can more quickly detect tire pressure abnormalities when the road conditions are poor, effectively prevent traffic accidents caused by tire failures, especially in bad road conditions, such as slippery curves, rugged mountain roads or congested sections, greatly reducing the probability of dangerous situations such as tire blowouts and loss of control due to tire pressure problems.

[0104] Figure 4 A schematic diagram of the structure of a tire pressure monitoring device according to an embodiment of the present application is shown. Exemplarily, the tire pressure monitoring device includes:

[0105] The road condition level determination module 100 is used to detect the road condition level according to the road condition level detection method, combined with the corresponding vehicle-mounted road condition information and the road condition level calculation rule; wherein the vehicle-mounted road condition information includes the first vehicle-mounted road condition information and the second vehicle-mounted road condition information.

[0106] The tire pressure monitoring frequency determination module 200 is used to determine the tire pressure monitoring frequency according to the road condition level, and control the wireless Bluetooth tire pressure monitoring device to monitor the tire pressure according to the tire pressure monitoring frequency.

[0107] It can be understood that the device of this embodiment corresponds to the tire pressure monitoring method of the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described repeatedly here.

[0108] The present application also provides a computer-readable storage medium for storing the computer program used in the above-mentioned vehicle. For example, the computer-readable storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0109] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0111] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.

[0112] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A tire pressure monitoring method, characterized in that: include: According to the road condition level detection method, the road condition level is detected in combination with the corresponding vehicle-mounted road condition information and the road condition level calculation rule; wherein the vehicle-mounted road condition information includes the first vehicle-mounted road condition information and the second vehicle-mounted road condition information; The tire pressure monitoring frequency is determined according to the road condition level, and the wireless Bluetooth tire pressure monitoring device is controlled to monitor the tire pressure according to the tire pressure monitoring frequency.

2. The tire pressure monitoring method according to claim 1, characterized in that: Before the method of determining the road condition level in accordance with the road condition level is combined with the corresponding vehicle-mounted road condition information and the road condition level calculation rule, the method further includes: Determining the road condition level detection method; If the road condition level is detected in a first manner, target vehicle-mounted road condition information for detecting the road condition level in accordance with the first manner is determined; wherein the target vehicle-mounted road condition information is one or more types of information in the first vehicle-mounted road condition information; the first vehicle-mounted road condition information includes acceleration information, angular velocity information, positioning information, and a front image; The method of detecting the road condition level in accordance with the road condition level detection method, in combination with the corresponding vehicle-mounted road condition information and the road condition level calculation rule, includes: Calculate the road condition value corresponding to each target vehicle-mounted road condition information respectively; The road condition level is calculated according to each road condition value in combination with the corresponding road condition level calculation rule.

3. The tire pressure monitoring method according to claim 2, characterized in that: The calculation of the road condition value corresponding to the acceleration information includes: An acceleration level is determined according to the vertical acceleration of the vehicle in the vertical direction in the acceleration information, and a corresponding first road condition value is determined according to the acceleration level.

4. The tire pressure monitoring method according to claim 2, characterized in that: The calculation of the road condition value corresponding to the angular velocity information includes: An angular velocity level is determined according to the angular velocity information, and a corresponding second road condition value is determined according to the angular velocity level.

5. The tire pressure monitoring method according to claim 2, characterized in that: The calculation of the road condition value corresponding to the positioning information includes: The current road condition of the vehicle is determined according to the positioning information and in combination with a map, and a third road condition value is determined according to the road condition.

6. The tire pressure monitoring method according to claim 2, characterized in that: The calculation of the road condition value corresponding to the front image includes: Preprocessing the front image to obtain a target front image; Inputting the target front image into an edge detection model, a texture feature extraction model, and an object recognition model respectively to obtain edge features, texture features, and obstacle features respectively; According to the edge features, texture features and obstacle features, lane line information, road surface flatness information and obstacle information are respectively obtained; A fourth road condition value is determined according to the lane line information, road surface flatness information and obstacle information.

7. The tire pressure monitoring method according to claim 2, characterized in that: Also includes: If the second method is used to detect the road condition level, the road condition level is detected according to the road condition level detection method in combination with the corresponding vehicle-mounted road condition information and the road condition level calculation rule, including: The road condition level is detected according to the second vehicle-mounted road condition information in combination with a fuzzy logic algorithm, a neural network algorithm or a decision tree algorithm; wherein the second vehicle-mounted road condition information includes the vehicle vibration amplitude and the compression and rebound frequency of the suspension system.

8. A tire pressure monitoring system, characterized in that: The vehicle includes a wireless Bluetooth tire pressure monitoring module, an on-board road condition monitoring module, a processor and a memory; The wireless Bluetooth tire pressure monitoring module is connected to the processor and is used to detect the tire pressure of the vehicle and transmit it to the processor; The vehicle-mounted road condition monitoring module is connected to the processor, and acquires the vehicle-mounted road condition information of the vehicle by detecting the vehicle and sends the information to the processor; The memory stores a computer program, and the processor is configured to execute the computer program to implement the tire pressure monitoring method according to any one of claims 1 to 7.

9. The tire pressure monitoring system according to claim 8, characterized in that: The vehicle-mounted road condition monitoring module includes an acceleration sensor, a gyroscope, a positioning module, a camera, an image processing module and an air spring extension acceleration sensor; The acceleration sensor is used to measure the acceleration information of the vehicle; the gyroscope is used to measure the angular velocity information of the vehicle; the positioning module is used to obtain the positioning information of the vehicle; the camera is used to capture the front image of the vehicle; the image processing module is used to process the front image; the air spring extension acceleration sensor is used to detect the compression and rebound frequency of the suspension system of the vehicle; The wireless Bluetooth tire pressure monitoring module includes a pressure sensor and a Bluetooth communication module; The pressure sensor is used to detect the tire pressure of the vehicle; and the Bluetooth communication module is used to transmit the tire pressure detected by the pressure sensor to the processor.

10. A computer-readable storage medium, characterized in that: The computer program is stored therein, and when the computer program is executed on a processor, the tire pressure monitoring method according to any one of claims 1 to 7 is implemented.

Images