江苏大学学报（自然科学版）2012，Vol.33Issue(2)：144-149,6.DOI:10.3969/j.issn.1671-7775.2012.02.005
边缘特征与局部纹理特性融合的阴影消除算法
Shadow elimination method integrated edge features and local texture characteristic
摘要
Abstract
To achieve shadow elimination in video target segmentation, according to confidence, characters of foreground edge projection and local texture features were merged to propose a novel shadow extraction strategy. By adaptive Gaussian method, the foreground containing shadow was obtained to extract dynamic background. The edge difference between foreground and background in minimum enclosing rectangle area of foreground was calculated to achieve edges and shadow of vehicle. Otsu algorithm was used for video segmentation. The area with high confidence was labeled as shadow, and that with low confidence was labeled as vehicle. According to the jumping level of local texture between current frame and background frame, the remaining shadow concerning with vehicle was found out in the area with middle confidence by further processing. Experimental results demonstrate that the proposed method can effectively remove huge shadows which may lead to heavy deformation with over 90% elimination rate. The algorithm can be applied in object detecting and tacking in intelligent video surveillance system with good real-time performance.关键词
智能交通系统/阴影消除/车辆跟踪/特征融合/纹理/高斯分布Key words
intelligent transportation system/ shadow elimination/ vehicle tracking/ features integrating/textures/ Gaussian distribution分类
交通工程引用本文复制引用
蔡英凤,张为公,王海..边缘特征与局部纹理特性融合的阴影消除算法[J].江苏大学学报（自然科学版）,2012,33(2):144-149,6.基金项目
国家科技支撑计划项目(2009BAG13A04) （2009BAG13A04）
江苏省自然科学基金资助项目(BK2010239) （BK2010239）
