Recognizing method and system for safety belt

Abstract

The invention discloses a method for detecting and recognizing the tying of a safety belt of a driver based on interval-maximizing and multi-sample dictionary learning. The method comprises the following steps: treating a driver-containing data-concentrated part of a windshield of a left half car as an image to be processed for input; acquiring a feature vector representation of each image; performing dictionary learning process for a training data set by an interval-maximizing and multi-example manner; respectively training an SVM (Support Vector Machine) multi-classifier for each type in the training data set after clustering to obtain a classifying model; coding the training data through the acquired dictionary; training the classifier through the coded feature vectors; detecting and recognizing an image to be recognized through the trained classifier, so as to determine whether the safety belt is tied from the image to be recognized. According to the recognizing method and system for the safety belt, the safety belt can be simply and easily detected and recognized, the popularization capacity is high, the detection and recognition accuracy is high, and the speed is fast; in addition, the influences of illumination and noise and other adverse factors can be effectively overcome.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a safety belt recognition method and system based on interval maximization multi-instance dictionary learning. Background technique [0002] With the continuous development of the global economic situation, people's living standards are improving day by day, the number of privately owned motor vehicles is increasing geometrically, and the popularization of cars has become an inevitable trend. Then comes the supervision and management of automobile safety. The wearing of driver's seat belt is the first work that needs to be supervised and managed. Therefore, it is particularly urgent and important to study the detection and identification of driver's seat belt. At present, the research on seat belt detection and recognition is not very perfect. The previous seat belt detection algorithm mainly relies on simple image processing algorithms such as edge detect...

AI Technical Summary

Problems solved by technology

[0003] However, there are still many problems in seat belt detection at present, such as the influence of the angle and light when the image is taken, and the influence of the contrast difference between the driver's clothing color and the seat belt color

These factors will have a negative impact on seat belt detection

Images