Traffic monitoring image-based automatic detection system for safety belt non-fastening behavior of driver

Abstract

The invention provides a traffic monitoring image-based automatic detection system for a safety belt non-fastening behavior of a driver. The system comprises a module for extracting a to-be-detected region of the safety belt and a module for judging whether the driver fastens the safety belt or not; the module for extracting the to-be-detected region of the safety belt comprises a license plate detection sub-module, a driver region extraction sub-module, an image enhancement sub-module, a human face detection sub-module and a safety belt detection region extraction sub-module; the module for judging whether the driver fastens the safety belt or not adopts a straight line detection-based safety belt judgment method; and the straight line detection-based safety belt judgment method is used for detecting an edge straight line section of the safety belt by using a Canny edge detection algorithm and a progressive probabilistic Hough transform straight line detection algorithm. The safety belt non-fastening behavior of the driver can be accurately and quickly detected and recorded, so that the disadvantages of high labor cost of manual identification, easy fatigue, easy negligence and the like are effectively overcome, and the safety belt non-fastening driving behavior of the driver is effectively inhibited.

Description

technical field [0001] The invention relates to an automatic detection system for drivers not wearing seat belts, in particular to an automatic detection system for drivers not wearing seat belts based on traffic monitoring images, and belongs to the technical field of intelligent monitoring and processing of road traffic violations. Background technique [0002] A car seat belt is a vehicle safety device whose purpose is to prevent harmful movements of the human body that may cause injury or death in the event of a car collision or sudden stop. The function of the seat belt is to reduce the possibility of death and serious injury in traffic accidents by reducing the secondary impact when the human body collides with the interior of the car. By maintaining the correct position of the wearer, the airbag can be used to maximize its effectiveness, and it can prevent the driver and occupants from being ejected from the vehicle when the vehicle crashes or rolls over. During trav...

AI Technical Summary

Problems solved by technology

[0006] However, for the application in the field of automatic detection of not wearing a seat belt, the existing technology is rarely used in actual traffic scenarios

The existing technology has some difficulties in realizing the automatic detection of not wearing a seat belt: First, it is difficult to obtain high-quality images. High-quality image data greatly increases the difficulty of recognition; secondly, it is difficult to recognize the target to be detected: the position of the seat belt is very different in a large truck and a car, and the way of wearing a seat belt is different for each person. It will cause errors in the positioning of the seat belt area and cause wrong identification; third, certain colors and stripes of the driver's clothes will affect the identification and reduce the accuracy of identification; fourth, in the actual monitoring scene, there are many Interference from changes in external factors, such as environmental lighting changes, including light gradients and light mutations, etc.; motion changes, camera position shake caused by bad weather, periodic motion of background objects such as leaves, ripples, etc., changes in the background shape, this It is particularly prominent in traffic scenes where seat belts are not automatically detected; fifth, there are still many difficulties in vehicle detection, including the impact of dynamic scenes. In actual traffic monitoring scenes, background images are often not static, which can easily lead to large The complex interference of the range seriously increases the difficulty of vehicle detection; the influence of occlusion and adhesion, the occlusion between objects will cause objects to stick to each other, which will cause difficulties in feature matching in target tracking. When there are multiple objects in the video image, it is inevitable. There will be mutual occlusion and adhesion, which will interfere with vehicle tracking; Sixth, it is difficult to realize the overall design of the automatic detection system for not wearing a seat belt, and the system architecture design, outline design, and software function implementation are relatively complicated

Images