iDistance Based Interactive Visual Surveillance Retrieval Algorithm

摘要：

This paper proposes an iDistance based interactive retrieval algorithm to accomplish semantic retrieval in visual surveillance system and improve the retrieval performance. The concept of user is interactively learned by training a SVM classifier from the user feedbacks. The search range of the algorithm is re duced by an iDistance based optimization algorithm. The surveillance objects are characterized by the color, texture and coefficient trajectory features. Experimen tal results on real scenes demonstrate the effectiveness of the proposed algorithm.

作者: Lin Qu Yaowu Chen Xiaofan Yang

作者单位: Institute of Advanced Digital Technology and Instrumentation, Zhejiang University, China Hangzhou Applied Acoustics Research Institute, Hangzhou, China

会议类型: 国际会议

会议名称: International Conference on Intelligent Computation Technology and Automation(2008 智能计算技术与自动化国际会议 ICICTA 2008)

会议地点: 长沙

会议语种:英文

页码: 71-75

在线出版日期: 2008-10-20（万方平台首次上网日期，不代表论文的发表时间）