Traffic video vehicle identification method based on SRC and SVM combined classifier

Abstract

The invention discloses a traffic video vehicle identification method based on an SRC and support vector machine (SVM) combined classifier. The histogram of oriented gradient (HOG) features of the vehicle samples are trained by a dictionary training (K-SVD) algorithm to obtain a redundant dictionary, so that the sparse representation-based classifier (SRC) is constructed, and meanwhile, the HOG features of the vehicle positive and negative samples and samples to be classified are subjected to sparse reconstruction, and the SVM is trained by the reconstructed features. At the end, the combined classifier is formed by the linear weighting of the SRC and the SVM based on reconstruction to complete the comprehensive decision of vehicle identification. According to the invention, the identification rate and robustness of the whole system in the complex traffic scenes of adhesion, shielding, and target category diversity, and the training time is reduced.

Description

technical field [0001] The invention relates to a traffic video vehicle recognition method based on a combined classifier of SRC and SVM, belonging to the technical field of image recognition. Background technique [0002] With the development of my country's economy and society, the population of cities and the number of motor vehicles have increased sharply, and the traffic flow has increased day by day. Traffic problems have become a major social problem in urban management and are one of the important reasons that hinder and restrict urban development. one. Therefore, relevant departments continue to strengthen the construction of transportation infrastructure, among which, Intelligent Transportation System (Intelligent Transportation System, ITS) came into being. The so-called intelligent transportation system is to make full use of modern high-tech under the existing traffic conditions to carry out reasonable traffic demand allocation and management, through various te...

AI Technical Summary

Problems solved by technology

[0007] Purpose of the invention: Aiming at the problems and deficiencies of low recognition rate and poor real-time performance in the prior art, the present invention provides a method for traffic video vehicle recognition based on SRC and SVM combined classifiers, using sparse reconstruction to remove redundant information, Reduce SVM training time and algorithm complexity, and combine SRC classifiers to make weighted comprehensive judgments. The combination of these two classifiers is complementary, and can simultaneously have the anti-noise performance of SRC and the small-sample recognition ability of SVM, significantly improving the recognition of the entire system efficiency and robustness, shortening training time

Images