运动物体的阴影检测与分割  

Moving Object’s Shadow Detection and Segmentation Based on Video

作　　者：辛国江[1] 邹北骥[2] 刘相滨[3] 康晶[1] 

机构地区：[1]湖南大学计算机与通信学院,湖南长沙410082 [2]中南大学信息科学与工程学院,湖南长沙410083 [3]湖南师范大学图像识别与计算机视觉研究所,湖南长沙410081

出　　处：《工程图学学报》2007年第6期85-90,共6页Journal of Engineering Graphics

基　　金：国家自然科学基金资助项目(60573079);湖南省自然科学基金资助项目(03JJY6025);湖南省教育厅科研资助项目(03C227)

摘　　要：阴影检测与分割在基于视频的运动物体检测与提取中具有重要作用。为了准确检测与分割阴影,提出了基于体色向量匹配的阴影检测与分割算法。提取前景区域以后,运用亮度测试法去除亮度值高于对应背景区域的前景区域,然后预判断阴影区域,最后利用体色向量匹配提取阴影区域。另外,提出了亮度步长的方法来检测阴影中的半影。实验结果表明,算法在多数情况下对运动物体阴影检测与分割具有较好的鲁棒性,提高了检测与分割的速度。Shadow detection and segmentation plays an important role in moving object detection and retrieval based on video. To detect and segment the shadow accurately, an algorithm based on body color vector matching is presented. After the foreground is extracted, the luminance test is used to reduce the region that has higher intensity than the background. Then prejudge the shadow area. At last, the shadow area is obtained by body color vector matching. In additional, the luminance step is applied to detect the penumbra. The experimental results show that the algorithm is robust under most situations, and it can improve the speed of detection and segmentation.

关 键 词：计算机应用 阴影检测 体色向量匹配 亮度步长 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]