基于支持向量机监控视频遮挡树叶检测.docVIP

基于支持向量机监控视频遮挡树叶检测 　　摘 要: 　　 　　针对安防监控摄像头被树叶遮挡的问题，提出一种基于支持向量机(SVM)的视频树叶遮挡检测算法。该算法利用视频的时域特性，采用累积帧差法实现对视频中疑似树叶区域的分割，提取视频中某一帧图像的整个区域和疑似树叶区域的颜色信息与面积信息作为视频的特征，最后采用支持向量机进行建模并用于视频树叶遮挡的检测。在有限样本前提下，算法准确率能够达到84%。实验结果表明，所提算法对于有树叶遮挡的监控视频能够进行有效识别。 　　?ス丶?词:树叶遮挡检测；监控视频；累积帧差；支持向量机；颜色特征 　　 　　 　　?ブ型挤掷嗪?: TP391.41 　　 　　文献标志码:A 　　英文标题?? 　　 　　Support vector machine based approach for?? 　　 leaf occlusion detection in security surveillance video 　　?び⑽淖髡呙? 　　 　　 　　YUAN Yuan????1,2??*??, DING Sheng????1,2??, XU Xin????1,2??, CHEN Li????1,2?? 　　?び⑽牡刂?( 　　 　　 　　1.School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan Hubei 430065, China??;???? 　　2.Hubei Province Key Laboratory of Intelligent Information Processing and Real??time Industrial System?? 　　??(??Wuhan University of Science and Technology??)??, Wuhan Hubei 430065, China 　　 　　英文摘要)?? 　　Abstract: 　　 　　Aiming at the problem that the security surveillance cameras have been hidden by leaves, a leaf occlusion detection algorithm based on Support Vector Machine (SVM) was proposed. The algorithm contains three steps. First, the regions of the leaf existing in the video were segmented. The accumulated frame subtraction method was applied to achieve this purpose. Second, the color and area information of the whole video image and the segmented regions were extracted as the key features. Third, these features were used for modeling and detecting obstacle occlusion by SVM. For all the collected samples, the detection accuracy of this method can reach up to 84%. The experimental results show that the proposed algorithm can detect the leaf occlusion in security surveillance video effectively. 　　 　　英文关键词??Key words: 　　 　　leaf occlusion detection; surveillance video; accumulated inter??frame subtraction; Support Vector Machine (SVM); color feature?? 　　 　　 　　 　　 　　 　　0 引言?? 　　随着现代科技的快速发展以及计算机技术的进步，安防视频监控已经广泛地应用于人们的日常生产生活。截至2010年，北京市已安装26万余摄像头用于安防监控，黑龙江省已新建监控点27?B355个????［1］??