Driving fatigue detection system and method based on video monitoring

Abstract

The invention discloses a driving fatigue detection system and method based on video monitoring, and relates to the technical field of automobile safe driving, the system comprises a camera module, an image processing module, a fatigue detection module and an early warning module; the camera module is used for collecting video data in the vehicle driving process and inputting the video data to the image processing module. The image processing module comprises a gray processing sub-module, a noise processing sub-module and an image enhancement sub-module; the image processing module is used for extracting driving track characteristics of the vehicle based on the video data; the fatigue detection module comprises a lane line detection sub-module, a vehicle motion feature detection sub-module and a driving behavior feature detection sub-module; the fatigue detection module is used for detecting whether the driver is in a fatigue state or not according to the extracted driving track features. According to the invention, the fatigue state of the driver can be detected more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of automobile safe driving, and in particular to a driving fatigue detection system and method based on video monitoring. Background Art

[0002] With the rapid development of the transportation industry, the number of vehicles has increased dramatically, and traffic accidents have also occurred frequently. Fatigue driving is one of the important causes of traffic accidents. Fatigue driving refers to the phenomenon that after a long period of continuous driving, the driver's driving skills are reduced due to the decline of physiological and psychological functions, which in turn causes traffic accidents. Fatigue driving will seriously affect the driver's attention, reaction ability, judgment ability, etc., and increase the risk of operating errors and accidents. According to relevant statistics, traffic accidents caused by fatigue driving account for a high proportion, posing a serious threat to people's lives and property safety. Summary of the invention

[0003] The purpose of this application is to provide a driving fatigue detection system and method based on video monitoring, which can significantly improve the accuracy of fatigue driving detection.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a driving fatigue detection system based on video monitoring, including: a camera module and an image processing module, a fatigue detection module and an early warning module.

[0006] The camera module is used to collect video data during the vehicle's driving process and input the video data into the image processing module.

[0007] The image processing module includes a grayscale processing submodule, a noise processing submodule and an image enhancement submodule; the image processing module is used to extract the driving trajectory characteristics of the vehicle based on the video data.

[0008] The fatigue detection module includes a lane line detection submodule, a vehicle motion feature detection submodule and a driving behavior feature detection submodule; the fatigue detection module is used to detect whether the driver is in a fatigue state according to the extracted driving trajectory features.

[0009] Optionally, a warning module is also included, which is used to send a warning signal to the driver when it is detected that the driver is in a fatigue state.

[0010] Optionally, the grayscale processing submodule is used to convert the color image in the video data into a grayscale image based on a weighted average method and an average method.

[0011] Optionally, the noise processing submodule is used to remove noise in the grayscale image based on a filtering method; the filtering method includes mean filtering, median filtering, Gaussian filtering and bilateral filtering.

[0012] Optionally, the image enhancement submodule is used to enhance the grayscale image after noise removal by adopting histogram equalization, adaptive histogram equalization, logarithmic transformation and gamma correction to obtain a processed driving image.

[0013] Optionally, the lane line detection submodule is used to:

[0014] Based on the Canny edge detection method, edge detection is performed on the processed driving image to determine the edge area in the driving image; the edge area is the area in the driving image where the grayscale value or color value changes.

[0015] Based on the edge area in the driving image, Hough transform is adopted to determine the straight lane line in the driving image.

[0016] Based on the edge area in the driving image, a curved lane line in the driving image is determined by using polynomial fitting.

[0017] Optionally, the vehicle motion feature detection submodule is used to determine the motion trajectory of the vehicle based on each frame image in the video data using an optical flow method.

[0018] Optionally, the driving behavior feature detection submodule is used to: obtain time series data of vehicle speed and time series data of vehicle steering wheel angle; calculate vehicle acceleration based on the time series data of vehicle speed; calculate vehicle steering angle change rate based on the time series data of vehicle steering wheel angle; determine the driver's driving behavior based on the vehicle acceleration and the vehicle steering angle change rate.

[0019] In a second aspect, the present application provides a driving fatigue detection method based on video monitoring, the driving fatigue detection method comprising:

[0020] Collect video data while the vehicle is driving.

[0021] The video data is subjected to image processing to extract the driving track features of the vehicle.

[0022] According to the driving trajectory characteristics, based on the lane line detection submodule, the vehicle motion feature detection submodule and the driving behavior feature detection submodule, it is detected whether the driver is in a fatigue state.

[0023] Optionally, when it is detected that the driver is in a fatigue state, a warning signal is issued to the driver.

[0024] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0025] The present application provides a driving fatigue detection system and method based on video monitoring. The system adopts a collaborative working mode of multiple modules including a camera module, an image processing module, a fatigue detection module and an early warning module. This multi-module design enables the system to analyze the driver's state from multiple angles and levels, thereby improving the comprehensiveness and accuracy of the detection. The image processing module pre-processes the collected video data through sub-modules such as grayscale processing, noise processing and image enhancement. And extracts the driving trajectory features of the vehicle based on the video data. These features can reflect the driving stability of the vehicle and the driving behavior of the driver, providing an important basis for fatigue detection. The fatigue detection module includes a lane line detection sub-module, a vehicle motion feature detection sub-module and a driving behavior feature detection sub-module. These sub-modules detect the driver's driving state from different angles respectively, and fuse the detection results. Multi-feature fusion detection can more comprehensively evaluate the driver's fatigue level and improve the accuracy of detection. The driving fatigue detection system based on video monitoring in the present application can more accurately detect the driver's fatigue state. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A schematic diagram of the structure of a driving fatigue detection system based on video monitoring provided in Example 1 of the present application.

[0028] Figure 2 A flowchart of a driving fatigue detection method based on video monitoring is provided in Example 2 of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0031] Embodiment 1

[0032] like Figure 1 As shown, this embodiment provides a driving fatigue detection system based on video monitoring, which is characterized by comprising: a camera module and an image processing module, a fatigue detection module and an early warning module.

[0033] The camera module is used to collect video data during the vehicle's driving process and input the video data into the image processing module.

[0034] The image processing module includes a grayscale processing submodule, a noise processing submodule and an image enhancement submodule; the image processing module is used to extract the driving trajectory characteristics of the vehicle based on the video data.

[0035] The fatigue detection module includes a lane line detection submodule, a vehicle motion feature detection submodule and a driving behavior feature detection submodule; the fatigue detection module is used to detect whether the driver is in a fatigue state according to the extracted driving trajectory features.

[0036] In this embodiment, the camera module includes a front camera and an optional rear camera of the vehicle.

[0037] The front camera is installed at the front of the vehicle, for example, on the front bumper or the front windshield. Its function is to capture the driving video data in front of the vehicle in real time in order to detect the lane line and driving trajectory ahead.

[0038] The rear camera is installed at the rear of the vehicle, for example, on the rear bumper or rear windshield. Its function is to capture the driving video data behind the vehicle to achieve a more comprehensive analysis of the driving trajectory.

[0039] In some implementations of this embodiment, the image processing module may be specifically as follows:

[0040] The image processing module includes a grayscale processing submodule, a noise processing submodule and an image enhancement submodule. In addition, it also includes a video input interface for receiving raw video data collected by the front and rear cameras.

[0041] The grayscale processing submodule is used to convert the color image in the video data into a grayscale image based on the weighted average method and the average method.

[0042] Specifically, grayscale is the process of converting a color image into a grayscale image, usually using the following methods:

[0043] Weighted average method: weighted average is performed according to the weight of the RGB channels, such as the commonly used formula:

[0044] Gray=0.299×R+0.587×G+0.114×B\text{Gray}=0.299\times R+0.587\times G+0.114\times BGray=0.299×R+0.587×G+0.114×B.

[0045] Average method: directly take the average value of the RGB channels: Gray=R+G+B3\text{Gray}=\frac{R+G+B}{3}Gray=3R+G+B.

[0046] The noise processing submodule is used to remove noise in the grayscale image based on a filtering method; the filtering method includes mean filtering, median filtering, Gaussian filtering and bilateral filtering.

[0047] Specifically, the commonly used methods include: Mean filtering: Using the average value of the neighborhood pixels instead of the center pixel value can smooth the image, but it will blur the edges. In this algorithm, each element of the convolution kernel is 1, and the size is 3x3 or 5x5. Median filtering: Using the median of the neighborhood pixels instead of the center pixel value is suitable for removing salt and pepper noise; this algorithm sorts the pixel values ​​in the neighborhood and takes the middle value. Gaussian filtering: Using Gaussian distribution weights to weighted average the neighborhood pixels, the smoothing effect is better and some edge information can be retained; this algorithm is: the convolution kernel weight is calculated according to the Gaussian function, and the commonly used sizes are 3x3, 5x5. Bilateral filtering: Considering spatial proximity and pixel value similarity at the same time, it can better retain the edge; this algorithm: the convolution kernel weight combines spatial distance and pixel value difference.

[0048] The image enhancement submodule is used to enhance the grayscale image after noise removal by using histogram equalization, adaptive histogram equalization, logarithmic transformation and gamma correction to obtain a processed driving image. Common methods include:

[0049] 1) Histogram equalization: Enhance contrast by adjusting the grayscale histogram of the image. Algorithm: Redistribute pixel values ​​so that they are evenly distributed across all gray levels.

[0050] 2) Adaptive Histogram Equalization (CLAHE): Apply histogram equalization in local areas to avoid over-enhancement. Algorithm: Divide the image into small blocks, perform histogram equalization on each block, and smooth the boundaries.

[0051] 3) Logarithmic transformation: Use logarithmic function to compress the dynamic range of the image and enhance details. Algorithm:

[0052] where c is a constant.

[0053] 4) Gamma correction: adjust the brightness of the image and perform nonlinear transformation through the gamma function. Algorithm: Output = Inputγ\text{Output} = \text{Input}^\gammaOutput = Inputγ, where γ is the gamma value.

[0054] The following is a code example (using the OpenCV library):

[0055] Python

[0056] Copy code

[0057] import cv2

[0058] import numpy as np

[0059] #Read the image

[0060] image=cv2.imread('input_image.jpg')

[0061] #Grayscale

[0062] gray_image=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)

[0063] # Mean filter

[0064] mean_filtered_image=cv2.blur(gray_image,(3,3))

[0065] #Median filter

[0066] median_filtered_image=cv2.medianBlur(gray_image,3)

[0067] #Gaussian filter

[0068] gaussian_filtered_image=cv2.GaussianBlur(gray_image,(5,5),0)

[0069] #Bilateral filtering

[0070] bilateral_filtered_image=cv2.bilateralFilter(gray_image,9,75,75)

[0071] #Histogram equalization

[0072] equalized_image = cv2.equalizeHist(gray_image)

[0073] # Adaptive histogram equalization (CLAHE)

[0074] clahe = cv2.createCLAHE(clipLimit = 2.0, tileGridSize=(8, 8))

[0075] clahe_image = clahe.apply(gray_image)

[0076] # Logarithmic transformation

[0077] c = 255 / np.log(1 + np.max(gray_image))

[0078] log_transformed_image = c * np.log(1 + gray_image)

[0079] log_transformed_image = np.array(log_transformed_image, dtype=np.uint8) # Gamma correction

[0080] gamma = 2.0

[0081] gamma_corrected_image = np.array(255 * (gray_image / 255) ** gamma, dtype='uint8')

[0082] # Display the image

[0083] cv2.imshow('Gray Image', gray_image)

[0084] cv2.imshow('Mean Filtered Image', mean_filtered_image)

[0085] cv2.imshow('Median Filtered Image', median_filtered_image)

[0086] cv2.imshow('Gaussian Filtered Image', gaussian_filtered_image)

[0087] cv2.imshow('Bilateral Filtered Image',bilateral_filtered_image)

[0088] cv2.imshow('Equalized Image',equalized_image)

[0089] cv2.imshow('CLAHE Image',clahe_image)

[0090] cv2.imshow('Log Transformed Image',log_transformed_image)

[0091] cv2.imshow('Gamma Corrected Image',gamma_corrected_image)

[0092] cv2.waitKey(0)

[0093] cv2.destroyAllWindows()

[0094] The above is image preprocessing using the OpenCV library.

[0095] In some implementations of this embodiment, the fatigue detection module includes a lane line detection submodule, a vehicle motion feature detection submodule and a driving behavior feature detection submodule.

[0096] Wherein, the lane line detection submodule is used to:

[0097] Based on the Canny edge detection method, edge detection is performed on the processed driving image to determine the edge area in the driving image; the edge area is the area in the driving image where the grayscale value or color value changes.

[0098] Based on the edge area in the driving image, Hough transform is adopted to determine the straight lane line in the driving image.

[0099] Based on the edge area in the driving image, a curved lane line in the driving image is determined by using polynomial fitting.

[0100] In the field of image processing and computer vision, edge detection is a commonly used technique to identify the boundaries of objects in an image. Specifically, Canny edge detection is a widely used edge detection method based on a multi-stage detection algorithm, including steps such as noise filtering, calculating gradients, non-maximum suppression, and double threshold detection. This method is effective in detecting edges in images, especially those areas with significant brightness changes. In edge detection, an edge refers to a place in an image where there is a significant change in grayscale or color values, and these changes usually correspond to the boundaries of an object.

[0101] For lane detection, edge features are usually manifested as a clear brightness contrast between the road and the lane. In order to detect straight lines in an image, the Hough transform can be used. However, for curved lanes, the traditional Hough transform may not accurately describe their shapes. In this case, polynomial fitting (such as a quadratic polynomial) can be used to describe the curved part of the lane. Through the edge detection results, the points on the lane can be extracted, and then curve fitting can be performed to obtain a more accurate lane model.

[0102] In addition to traditional image processing methods, deep learning methods have also shown great potential in lane detection. Convolutional neural networks (CNNs) are powerful deep learning models that are particularly suitable for image recognition and classification tasks. In lane detection, end-to-end CNNs models, such as U-Net and SegNet, can learn and predict the location of lanes directly from raw images. These models can extract features from images through multi-layer convolution and pooling operations, and are trained through back-propagation algorithms to achieve high-precision lane detection.

[0103] In addition, instance segmentation methods such as Mask R-CNN have also been applied to lane detection. Instance segmentation can not only identify lanes in an image, but also distinguish them from other objects. Mask R-CNN achieves accurate segmentation of lanes by classifying at the pixel level and generating a mask that each pixel belongs to the lane. This method can not only detect the existence of lanes, but also provide detailed shape and location information of lanes, which has important application value for autonomous driving and intelligent transportation systems.

[0104] The following is a code example based on OpenCV

[0105]

[0106] Among them, the vehicle motion feature detection submodule of the fatigue detection module is used to determine the motion trajectory of the vehicle based on each frame image in the video data using the optical flow method.

[0107] The extraction of vehicle motion features usually includes factors such as speed, acceleration, and steering angle. The methods include but are not limited to the following:

[0108] Kalman filter technology, which is widely used to estimate and track the position, speed and acceleration of vehicles. Optical flow method, which estimates the motion of pixels in an image and then derives the trajectory of the vehicle. Inertial measurement unit (IMU), which includes sensors such as accelerometers and gyroscopes, is used to accurately detect the acceleration and angular velocity of the vehicle.

[0109] The following is a sample code using OpenCV and optical flow method

[0110]

[0111]

[0112] Among them, the driving behavior feature detection submodule of the fatigue detection module is used to: obtain the time series data of the vehicle speed and the time series data of the vehicle steering wheel angle; calculate the vehicle acceleration according to the time series data of the vehicle speed; calculate the vehicle steering angle change rate according to the time series data of the vehicle steering wheel angle; determine the driver's driving behavior according to the vehicle acceleration and the vehicle steering angle change rate.

[0113] In the process of extracting driving behavior features, we usually focus on some key behavior features, such as sudden acceleration, sudden braking, and sharp turns. In order to accurately extract these features, the following methods can be used:

[0114] First, the speed change rate is an important indicator. By analyzing the time series data of vehicle speed, the change of acceleration can be calculated. This method can help detect whether the driver has sudden acceleration or sudden braking during driving. Specifically, by differentiating the speed data, the time series of acceleration can be obtained, and then a threshold is set. When the acceleration exceeds this threshold, it can be judged as sudden acceleration or sudden braking.

[0115] Secondly, the steering angle change rate is also a key feature. By analyzing the steering wheel angle data, the steering angle change rate can be calculated. This method can help detect whether the driver has made a sharp turn during driving. Specifically, by differentiating the steering wheel angle data, the time series of the steering angle change rate can be obtained, and then a threshold is set. When the steering angle change rate exceeds this threshold, it can be judged as a sharp turn.

[0116] Finally, driving mode classification is a more comprehensive approach. By using machine learning algorithms, the driver's driving behavior can be classified. Common machine learning algorithms include decision trees, random forests, and support vector machines (SVMs). These algorithms can learn the characteristics of driver behavior through training data and classify new driving behaviors. Specifically, a large amount of driving behavior data can be collected, including information such as speed, steering angle, acceleration, etc., and then the data can be used to train the machine learning model. Through the trained model, the driver's driving behavior can be classified to identify different driving modes, such as aggressive driving, smooth driving, etc.

[0117] The following is a code example for acceleration and sudden acceleration detection

[0118] Python

[0119] Copy code

[0120] import numpy as np

[0121] #Example speed data (unit: m / s)

[0122] speed_data=[0,2,4,6,8,10,12,15,20,22,20,18,16,14,12,10,8,6,4,2,0]

[0123] #Calculate acceleration

[0124] acceleration_data=np.diff(speed_data)

[0125] #Set the rapid acceleration threshold (unit: m / s^2)

[0126] acceleration_threshold=3

[0127] #Detect rapid acceleration

[0128] sudden_acceleration_events=np.where(acceleration_data>acceleration_threshold)[0]

[0129] print("The sudden acceleration event occurred at time point:", sudden_acceleration_events).

[0130] The above algorithms and methods can help build an effective driver fatigue detection system. In practical applications, multiple features and algorithms can be combined, and machine learning or deep learning models can be used to further improve detection accuracy and reliability.

[0131] In addition, in some implementations of this embodiment, the driving fatigue detection system further includes an early warning module for sending an early warning signal to the driver when it is detected that the driver is in a fatigue state.

[0132] Embodiment 2

[0133] This embodiment provides a driving fatigue detection method based on video monitoring, and the driving fatigue detection method includes:

[0134] Step 201: Collect video data of the vehicle during driving.

[0135] Step 202: Perform image processing on the video data to extract the driving trajectory features of the vehicle.

[0136] Step 203: According to the driving trajectory characteristics, based on the lane line detection submodule, the vehicle motion feature detection submodule and the driving behavior feature detection submodule, detect whether the driver is in a fatigue state.

[0137] Step 204: When it is detected that the driver is in a fatigue state, a warning signal is issued to the driver.

[0138] In summary, this application has the following technical effects:

[0139] 1) Contactless detection: The detection system based on video and vehicle motion characteristics of this application collects data by installing a camera and using the vehicle's existing sensors (such as vehicle speed sensors, accelerometers, etc.), without the need for direct contact with the driver. This feature makes it more convenient and comfortable in practical applications, reducing interference with the driver.

[0140] 2) Comprehensive analysis: The method provided in this application can comprehensively analyze the vehicle's driving trajectory, vehicle motion characteristics (such as speed, acceleration, steering angle, etc.) and driving behavior characteristics (such as sudden acceleration, sudden braking, sharp turns, etc.). Through comprehensive analysis of multiple data sources, the driver's fatigue state can be detected more accurately, reducing the possibility of false alarms and missed alarms.

[0141] 3) Strong real-time performance: This application uses cameras and vehicle sensors to collect and analyze data, which can achieve real-time detection and early warning. When the system detects that the driver may be fatigued, it can immediately issue an alarm to help the driver take timely measures to prevent accidents.

[0142] 4) Strong environmental adaptability: The detection system based on video and vehicle motion features of this application can adapt to different driving environments. Whether it is day or night, whether it is a city road or a highway, this method can effectively detect. In addition, the accuracy of detection can be further improved by analyzing environmental features such as road type and traffic flow.

[0143] 5) Relatively low cost: Compared with some high-precision physiological signal detection equipment (such as brain wave detectors, ECG monitoring equipment, etc.), the detection system based on video and vehicle motion characteristics is relatively low in cost. Modern vehicles are usually equipped with a variety of sensors and cameras, which can be directly used for driving fatigue detection, reducing the investment in additional equipment.

[0144] 6) Privacy protection: Since this application does not need to collect the driver's physiological signals, this method has the advantage of privacy protection. The driver does not need to worry about the leakage or misuse of physiological data.

[0145] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0146] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A driving fatigue detection system based on video monitoring, characterized in that: include: Camera module and image processing module, fatigue detection module and early warning module; The camera module is used to collect video data during the vehicle's driving process and input the video data into the image processing module; The image processing module includes a grayscale processing submodule, a noise processing submodule and an image enhancement submodule; the image processing module is used to extract the driving trajectory characteristics of the vehicle based on the video data; The fatigue detection module includes a lane line detection submodule, a vehicle motion feature detection submodule and a driving behavior feature detection submodule; The fatigue detection module is used to detect whether the driver is in a fatigue state according to the extracted driving trajectory features.

2. The driving fatigue detection system based on video monitoring according to claim 1 is characterized in that: It also includes a warning module, which is used to send a warning signal to the driver when it is detected that the driver is in a fatigue state.

3. The driving fatigue detection system based on video monitoring according to claim 2 is characterized in that: The grayscale processing submodule is used to convert the color image in the video data into a grayscale image based on a weighted average method and an average method.

4. The driving fatigue detection system based on video monitoring according to claim 3 is characterized in that: The noise processing submodule is used to remove noise in the grayscale image based on a filtering method; the filtering method includes mean filtering, median filtering, Gaussian filtering and bilateral filtering.

5. The driving fatigue detection system based on video monitoring according to claim 4 is characterized in that: The image enhancement submodule is used to enhance the grayscale image after noise removal by adopting histogram equalization, adaptive histogram equalization, logarithmic transformation and gamma correction to obtain a processed driving image.

6. The driving fatigue detection system based on video monitoring according to claim 5 is characterized in that: The lane line detection submodule is used to: Based on the Canny edge detection method, edge detection is performed on the processed driving image to determine the edge area in the driving image; the edge area is an area in the driving image where the grayscale value or color value changes; Based on the edge area in the driving image, a Hough transform is used to determine the straight lane line in the driving image; Based on the edge area in the driving image, a curved lane line in the driving image is determined by using polynomial fitting.

7. The driving fatigue detection system based on video monitoring according to claim 6 is characterized in that: The vehicle motion feature detection submodule is used to determine the motion trajectory of the vehicle based on each frame image in the video data using an optical flow method.

8. The driving fatigue detection system based on video monitoring according to claim 1 is characterized in that: The driving behavior feature detection submodule is used to: obtain time series data of vehicle speed and time series data of vehicle steering wheel angle; calculate vehicle acceleration based on the time series data of vehicle speed; calculate vehicle steering angle change rate based on the time series data of vehicle steering wheel angle; and determine the driver's driving behavior based on the vehicle acceleration and the vehicle steering angle change rate.

9. A driving fatigue detection method based on video monitoring, characterized in that: The driving fatigue detection method comprises: Collect video data during vehicle driving; Performing image processing on the video data to extract driving trajectory features of the vehicle; According to the driving trajectory characteristics, based on the lane line detection submodule, the vehicle motion feature detection submodule and the driving behavior feature detection submodule, it is detected whether the driver is in a fatigue state.

10. The method for detecting driving fatigue based on video monitoring according to claim 9, characterized in that: When it is detected that the driver is in a fatigue state, a warning signal is sent to the driver.

Images