The state-of-the-art research progress on motion segmentation
- 信息技术－会议论文 
Motion segmentation is currently one of the most active research topics in the areas of computer vision and multimedia. It has a wide spectrum of potential applications, including action recogn-ition, visual surveillance, video indexing, video compression, and many other applications. In this paper, we review the recent deve-lopments (especially for those in recent five years) of motion seg-mentation methods and analyze their respective pros and cons. Several valuable research directions are discussed and some sugg-estions are put forward in the end. Categories and Subject Descriptors I.2.10 [Vision and Scene Understanding]: Motion; I.4.8 [Scene Analysis]: Motion General Terms Algorithms, Performance. Copyright 2014 ACM.