Active Trace: A Sparse Spatiotemporal Representation for Videos
Han Z(韩志); Shen GP(沈贵萍); Ding ND(丁乃达); Tian JD(田建东); Yu SQ(余思泉); Tang YD(唐延东)
刊名IEEE Access
2017
卷号5页码:22433-22442
关键词active trace video modeling sparse representation tracking action template
ISSN号2169-3536
通讯作者Han Z(韩志)
产权排序1
中文摘要This paper proposes a sparse video representation with a deformable spatiotemporal template feature, named as active trace template. An active trace is the motion track of an active spatial feature which moves in a certain velocity. To accommodate geometric variations of the spatial feature and motion variations of the temporal track, the atomic spatial feature in each video frame is capable to slightly shift its location and other attributes within certain ranges to best represent the salient trackable structure. The representation quality is quantified by a spatiotemporal score. It is computed through a new proposed spatiotemporal hierarchical architecture of summax maps. Based on the score, a small number of best active trace templates are selected from all the trace candidates to depict the video sketch. The experiments demonstrate that for natural videos, the proposed model is able to provide an intuitive and sparse representation which matches human vision as well as reveals the spatiotemporal correspondence along consecutive frames, even in challenging situations such as occlusion. Furthermore, it shows the potential on dealing with high level vision tasks by moving object detection and segmentation, and action template learning and representation. OAPA
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
研究领域[WOS]Computer Science ; Engineering ; Telecommunications
关键词[WOS]OBJECT TRACKING ; VISUAL TRACKING ; MODEL
收录类别SCI ; EI
语种英语
WOS记录号WOS:000414737100001
内容类型期刊论文
源URL[http://ir.sia.cn/handle/173321/21110]  
专题沈阳自动化研究所_机器人学研究室
作者单位State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式
GB/T 7714
Han Z,Shen GP,Ding ND,et al. Active Trace: A Sparse Spatiotemporal Representation for Videos[J]. IEEE Access,2017,5:22433-22442.
APA Han Z,Shen GP,Ding ND,Tian JD,Yu SQ,&Tang YD.(2017).Active Trace: A Sparse Spatiotemporal Representation for Videos.IEEE Access,5,22433-22442.
MLA Han Z,et al."Active Trace: A Sparse Spatiotemporal Representation for Videos".IEEE Access 5(2017):22433-22442.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。


©版权所有 ©2017 CSpace - Powered by CSpace