期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：48
期号：2
页码：1136-1143
出版社：Journal of Theoretical and Applied
摘要：This article topics based on multi-feature fusion the Mean shift target tracking technology belongs to the field of intelligent video analysis, moving target tracking is interested in moving target location each image in a video sequence to find and acquire the target movement. Moving target tracking problem can be stated as interested in moving target movement prediction in the video sequence, feature extraction, feature matching and template update problem. In this paper, we consider using compressed domain features as a complement of the color features to extract the compressed domain features first need to understand the compressed domain detection technology. Detection based on the compressed domain, that is, in the case of not decoding or a small amount of decoding, directly on the compression characteristics of the image analysis, in order to achieve the detection of the image moving object.
关键词：Mean shift; Target tracking; Multi-feature fusion; Target recognition; Communication system
