Real-Time Moving Object Classification with Automatic Scene Division

CASIA OpenIR > 09年以前成果

	Real-Time Moving Object Classification with Automatic Scene Division
	Zhaoxiang Zhang; Yinghao Cai; Kaiqi Huang; Tieniu Tan
	2007-09-16
会议名称	IEEE International Conference on Image Processing
会议录名称	16 Sep - 19 Sep 2007
会议日期	16-19 September 2007
会议地点	San Antonio, Texas, USA
摘要	We address the problem of moving object classification. Our aim is to classify moving objects of traffic scene videos into pedestrians, bicycles and vehicles. Instead of supervised learning and manual labeling of large training samples, our classifiers are initialized and refined online automatically. With efficient features extracted and organized, the approach can be real-time and achieve high classification accuracy. Once the view or scene changes detected, the algorithm can automatically refine the classifiers and adapt them to new environments. Experimental results demonstrate the effectiveness and robustness of the proposed approach.
关键词	Surveillance Pattern Classification Object recognition Motion Detection Video Signal Processing
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/10989
专题	09年以前成果
通讯作者	Zhaoxiang Zhang
推荐引用方式 GB/T 7714	Zhaoxiang Zhang,Yinghao Cai,Kaiqi Huang,et al. Real-Time Moving Object Classification with Automatic Scene Division[C],2007.