Transferring Training Instances for Convenient Cross-View Object Classification in Surveillance

CASIA OpenIR > 智能感知与计算研究中心

	Transferring Training Instances for Convenient Cross-View Object Classification in Surveillance
	Zhaoxiang Zhang; Yuhang Zhao; Yunhong Wang; Jianyun Liu; Zhenjun Yao; Jun Tang
发表期刊	IEEE Transactions on Information Forensics and Security
	2013-05-29
卷号	8 期号:10 页码:1632-1641
摘要	Automatic object classification is an important issue in traffic scene surveillance. Appearance variation due to perspective distortion is one of the most difficult problems for moving object detection, tracking, and recognition. We propose an active transfer learning approach to bridge the gap between appearance variations under two different scenes. Only a small number of training samples are required in the target scene, which can be combined with transferred samples of the source scene to achieve a reliable object classifier in the target scene, and active learning strategy makes the algorithm more efficient. Abundant experiments are conducted and experimental results demonstrate the effectiveness and convenience of our approach.
关键词	Transfer Learning Active Learning Cross-view Object Classification Surveillance
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13202
专题	智能感知与计算研究中心
通讯作者	Zhaoxiang Zhang
推荐引用方式 GB/T 7714	Zhaoxiang Zhang,Yuhang Zhao,Yunhong Wang,et al. Transferring Training Instances for Convenient Cross-View Object Classification in Surveillance[J]. IEEE Transactions on Information Forensics and Security,2013,8(10):1632-1641.
APA	Zhaoxiang Zhang,Yuhang Zhao,Yunhong Wang,Jianyun Liu,Zhenjun Yao,&Jun Tang.(2013).Transferring Training Instances for Convenient Cross-View Object Classification in Surveillance.IEEE Transactions on Information Forensics and Security,8(10),1632-1641.
MLA	Zhaoxiang Zhang,et al."Transferring Training Instances for Convenient Cross-View Object Classification in Surveillance".IEEE Transactions on Information Forensics and Security 8.10(2013):1632-1641.