Fast adaptation method for traffic video monitoring target detection based on machine vision

Abstract

The invention belongs to the field of machine vision and intelligent control for achieving fast self-adaptation of traffic video monitoring target detection. The method comprises the steps of building an initial training sample bank; training an AdaBoost classifier based on Haar characteristics and a support vector machine (SVM) classifier based on histograms of oriented gradients (HOG) characteristics respectively; and detecting monitoring images frame by frame by employing of the two classifiers, wherein the detection process is divided into steps of predicting of sub-images in a detection frame through the two classifiers respectively, performing of confidence-degree determination on predicted results, adding of prediction labels corresponding to large confidence-degree and the sub-images into additional training sample banks of the classifiers corresponding to small confidence-degree till the size of the detection frame reaches half the sizes of detected images, retraining of the two classifiers by using the updated training sample banks and detecting of a next frame of image till all images are detected, and the final classifiers can be used for detecting targets of vehicles, pedestrians and the like in actual traffic scenes.

Description

technical field [0001] The invention belongs to the field of machine vision and intelligent control, and is an invention for detecting traffic video monitoring targets by using computer technology, image processing technology, machine learning technology and pattern recognition technology. Background technique [0002] Accurate and real-time detection of monitoring targets such as pedestrians and vehicles in traffic videos is the fundamental guarantee for subsequent traffic video processing such as target tracking and behavior analysis. There have been many related researches on object detection in traffic video surveillance, and most of them currently use machine learning methods in pattern recognition for object detection. As long as the target image to be detected is added to the positive sample library of the training sample library, the complex background is added to the negative sample library of the training sample library, an appropriate classifier is selected to lea...

AI Technical Summary

Problems solved by technology

Such a process requires a lot of time and labor costs, and it is difficult to obtain a comprehensive sample library.

Images