Vehicle detection method based on multi-component space position relation GMM (Gaussian Mixture Modeling)

Abstract

The invention discloses a vehicle detection method based on multi-component space position relation GMM (Gaussian Mixture Modeling). The method comprises the following steps: training color features of a license plate and a pair of rear lamps to obtain conversion models specific to color images and gray images, and processing original road traffic video images by the conversion models respectively to obtain gray images highlighting a license plate area and rear lamp areas; performing threshold segmentation and connected component analysis on the grey image of the pair of rear lamps to finish further accurate positioning of the pair of rear lamps; and lastly, building a position relationship probability model for detection results of the pair of rear lamps and the license plate on the same space according to a GMM theory, and further judging whether targets constructed by detected components refer to the same vehicle or different vehicles so as to finish accurate recognition of vehicles. The method has relatively high stability and detection accuracy, and has a relatively good effect particularly for the situations of poor light conditions and component shielding.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, and relates to a vehicle detection method based on multi-component spatial position relationship GMM modeling. Background technique [0002] With the vigorous promotion of intelligent traffic monitoring system and the rapid development of computer vision technology, video-based vehicle detection and recognition has gradually become an important content of today's traffic monitoring system research. Accurate vehicle detection can provide certain support and guarantee for the intelligent monitoring and control of road traffic by the road traffic supervision department. [0003] The research on vehicle detection technology in road traffic monitoring system can be traced back to the 1970s, when the United States first proposed the idea of ​​using machine vision instead of traditional detection methods for vehicle detection. Later, with the continuous development of ITS, all countries in the...

AI Technical Summary

Problems solved by technology

[0004] However, many methods proposed for this idea are not yet mature, and there are still the following unsolvable problems

First, the complex urban environment, changeable weather, uneven lighting, etc. will reduce the performance of the detection

Second, when there is a traffic jam, mutual occlusion between vehicles will bring great difficulties to vehicle detection, and it often occurs that multiple vehicles are fused into one vehicle and detected

Third, the scattering from daytime light sometimes causes the shadow of the target to be misdetected as a vehicle target

Images