Rear-view vehicle detection based on MSER and spatial combination feature description

Abstract

With the rapid development of smart city and intelligent transportation systems(ITS), traffic surveillance plays an important role on traffic and city safety. However, due to the variation of the illumination conditions and complex urban scenarios, camera-based vehicle detection becomes an emerging and challenging problem. In this paper, an effective and robust framework of rear-view vehicle detection for complex urban surveillance is proposed. Firstly, original image is decomposed into red-green-blue(RGB) color space with multi-channel enhancement technique. The region of interested (ROI) are then located by the unique color and texture utilizing maximally stable extremal region(MSER) algorithm. Furthermore, with special and relatively fixed spatial relationship of rear-lamp and license plate, a novel spatial combination feature (SCF) description is proposed. By utilizing the state-of-art support vector machine(SVM) on the proposed SCFs, the vehicle detection problem is recast into a supervised learning classification problem. The proposed method is fully evaluated and tested under different illumination conditions and real complex urban scenarios. Experimental results demonstrate the effectiveness and the robustness for the proposed detection framework.