中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 生物识别与安全技术研究中心
Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph

文献类型：期刊论文

作者Wen, Longyin1; Lei, Zhen2; Chang, Ming-Ching3; Qi, Honggang4; Lyu, Siwei1
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2017-04-01
卷号122期号:2页码:313-333
关键词Multi-camera Multi-target Tracking Single-camera Multi-target Tracking Space-time-view Hyper-graph Dense Sub-hypergraph Search
DOI10.1007/s11263-016-0943-0
文献子类Article
英文摘要Incorporating multiple cameras is an effective solution to improve the performance and robustness of multi-target tracking to occlusion and appearance ambiguities. In this paper, we propose a new multi-camera multi-target tracking method based on a space-time-view hyper-graph that encodes higher-order constraints (i.e., beyond pairwise relations) on 3D geometry, appearance, motion continuity, and trajectory smoothness among 2D tracklets within and across different camera views. We solve tracking in each single view and reconstruction of tracked trajectories in 3D environment simultaneously by formulating the problem as an efficient search of dense sub-hypergraphs on the space-time-view hyper-graph using a sampling based approach. Experimental results on the PETS 2009 dataset and MOTChallenge 2015 3D benchmark demonstrate that our method performs favorably against the state-of-the-art methods in both single-camera and multi-camera multi-target tracking, while achieving close to real-time running efficiency. We also provide experimental analysis of the influence of various aspects of our method to the final tracking performance.
WOS关键词MULTIPERSON TRACKING ; ALGORITHM ; TARGETS ; PEOPLE
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000398162200008
资助机构US National Science Foundation Research Grant(CCF-1319800) ; National Key Research and Development Plan(2016 YFC0801002) ; Chinese National Natural Science Foundation(61375037 ; National Nature Science Foundation of China(61472388) ; 61473291)
源URL[http://ir.ia.ac.cn/handle/173211/15082]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
作者单位1.SUNY Albany, Dept Comp Sci, Albany, NY 12222 USA
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
3.SUNY Albany, Dept Comp Engn, Albany, NY 12222 USA
4.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Wen, Longyin,Lei, Zhen,Chang, Ming-Ching,et al. Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2017,122(2):313-333.
APA Wen, Longyin,Lei, Zhen,Chang, Ming-Ching,Qi, Honggang,&Lyu, Siwei.(2017).Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph.INTERNATIONAL JOURNAL OF COMPUTER VISION,122(2),313-333.
MLA Wen, Longyin,et al."Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph".INTERNATIONAL JOURNAL OF COMPUTER VISION 122.2(2017):313-333.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。