QQ客服 官方微博 反馈留言

	A Novel Fast and Effictive Video Retrieval System for Surveillance Application
	Aixing Li; Fengqi Yu; Keqing Shi
	2011
会议名称	1st Annual IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems,
会议地点	Kunming, China
英文摘要	Fast and effective indexing and retrieval from large amount of surveillance videos are very important issues. This paper proposes a novel object-semantic-based surveillance video indexing and retrieval system, which is mainly composed of two modules: video analysis and video retrieval. In the video analysis, the systems first segments video objects (VO) fromsurveillance videos, and the fundamental semantic information is then extracted and indexed into the database. A normal approach of Gaussian Mixed Model (GMM) is applied in video object extraction (VOE) and video object segmentation (VOS). During retrieval, the query is converted to semantic information without re-processing the surveillance videos. Color, edge orientation histograms and SIFT (Scale Invariant Feature Transforms), as the key features and similarity measurement, are considered together to accurately match the video objects (VOM). The experiment shows that a user can retrieve the requiredvideos effectively.
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/3286]
专题	深圳先进技术研究院_集成所
作者单位	2011
推荐引用方式 GB/T 7714	Aixing Li,Fengqi Yu,Keqing Shi. A Novel Fast and Effictive Video Retrieval System for Surveillance Application[C]. 见:1st Annual IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, . Kunming, China.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。