Object based Video Retrieval with Local Feature and Color Feature

摘要：

This paper describes a method for video retrieval system based on local feature and color feature. In this paper, the local features are detected and described by SIFT, then tracked throughout the shot to form tracks and the colors of tracks are defined. A group algorithm is introduced to combine tracks with the same color into meaningful object clusters. Compared to A.Anjulans video retrieval approach, the proposed method is highly useful to group tracks. The significant improvement in performance is demonstrated.

关键词： Object retrieval Shot segmentation Color Feature definition Tracks clustering

作者: Lihua Xing Cui Xie

作者单位: Department of Computer Science and TechnologyOcean University of ChinaQingdao, China Department of Computer Science and Technology Ocean University of China Qingdao, China

会议类型: 国际会议

会议名称: 2011 International Conference on Information System and Computational Intelligence(2011 IEEE信息系统与计算智能国际会议 ICISCI 2011)

会议地点: 哈尔滨

会议语种:英文

页码: 202-206

在线出版日期: 2011-01-18（万方平台首次上网日期，不代表论文的发表时间）