A driver fatigue detection system and a fatigue detection method thereof
A driver fatigue detection system technology, applied in the driver fatigue detection system, fatigue detection field based on deep learning and information fusion, can solve the driver's driving operation is not friendly enough, the accuracy is not high, lag and other problems, to achieve real-time Accurate identification and detection, prevention of fatigue driving, and improvement of accuracy
Active Publication Date: 2019-05-10
LIANCHUANG AUTOMOBILE ELECTRONICS
View PDF6 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The current real-time fatigue detection technology for drivers mainly uses contact equipment to detect the driver's physiological signals. Affect the driver, but the accuracy is not high, the lag is serious
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0063] refer to figure 1 As shown, the driver fatigue detection system provided by the present invention includes: an image preprocessing module, a face and a facial feature point detection module, a facial area adjustment normalization module, a facial feature extraction network module and a fatigue degree judgment module;
[0064] The image preprocessing module converts the image into a single-channel grayscale image, and the image resolution is greater than 640×480;
[0065] The gray conversion formula is, Gray=0.299R+0.587G+0.114B;
[0066] refer to figure 2 As shown, the face and the facial feature point detection module adopt the multi-level cascaded convolutional neural network MTCNN to detect and obtain the facial area and facial feature points; make all the facial feature points output by the multi-level cascaded convolutional neural network MTCNN be located in the facial area Form the face position frame, then by the face position frame to the cropping of face reg...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a driver fatigue detection system. The system comprises an image preprocessing module for processing an image into a preset format; the face and face feature point detection module adopts a first convolutional neural network to detect and obtain a face region and face feature points; the face area adjusting and normalizing module forms a face position frame according to theface feature points, cuts the face area by using the face position frame, and normalizes the cut face area; the facial feature extraction network module adopts a second convolutional neural network to obtain facial features in the normalized image and obtain the confidence of each facial feature; and the fatigue degree and fatigue state judgment module is used for obtaining the current image fatigue degree according to the fatigue judgment rule and obtaining the driver fatigue state by utilizing a PERCLOS algorithm according to the previous image fatigue degree. The invention also discloses adriver fatigue detection method. The face information of the driver can be accurately acquired, and the fatigue state of the driver can be accurately judged by performing a fusion decision.
Description
technical field [0001] The invention relates to the field of automobiles, in particular to a driver fatigue detection system based on deep learning and information fusion. The invention also relates to a fatigue detection method based on deep learning and information fusion. Background technique [0002] According to research at home and abroad, fatigue driving is one of the three major causes of major accidents: traffic accidents caused by fatigue driving account for more than 40%, followed by drunk driving, vehicle failure, and violation of traffic regulations. Driving fatigue refers to the disorder of physiological or psychological functions of the driver due to various reasons when driving a vehicle (that is, physical or psychological fatigue), which weakens the driver's perception of the surrounding environment and the ability to control the vehicle. Descent, deviation from normal driving behavior. Therefore, how to actively monitor the driver's state and effectively ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06N3/04G06N3/08
Inventor 谢鹏陈刚李祥危刚
Owner LIANCHUANG AUTOMOBILE ELECTRONICS