一种基于颜色和纹理特征的阴影检测新方法.docVIP

  A Novel Shadow Detection Method Based on Color and Texture Features Li Qiaohong, Zhang Honggang, Gu Fang, Dai Yourui, Yu Jie** 5 10 (Pattern Recognition and Intelligent System Lab, Beijing University of Posts and Telecommunications, Beijing 100876) Abstract: This paper describes a new method for shadow detection of moving objects in video surveillance applications, improving the detection performance and fascinating the following image processing steps, such as object tracking, classification and behavior analysis. This method is based on the priori that shadow region and background region share the similar textural and chromatic characteristics. This method combines the virtues of color and texture features, to select the best criterion to discriminate shadow pixels from object pixels. Experiment shows that this method can achieve desirable performance under indoor and outdoor environment. Keywords: shadow removal; shadow detection; HSV; LBP; ITS 15 0 Introduction Object detection and tracking is an essential research realm in Intelligence Transportation Systems (ITS) involving image processing, pattern recognition, machine learning technology, which is a crucial problem to implementing efficient supervision and management of road traffic 20 25 30 35 40 infrastructures [1]. Massive research has been investigated since the late 1980s, but there is still plenty of work going on. Despite of the intense interests of researchers, government and industry managers, existing video surveillance systems still suffer from poor reliability, high cost and unbalanced accuracy [2]. There are many complex problems, illumination change, occlusions, extreme weather, perspective collimation, shadows, causing a lot of errors. Shadow is a region of relative darkness within an illuminated region, produced when an object totally or partially intercepts the light path from the illumination source to the surface obtained by the camera [3]. Shadows can be divided into two categori