On collaborative people detection and tracking in complex scenarios

被引：14
作者：
Garcia-Martin, Alvaro [1 ]
Martinez, Jose M. [1 ]
机构：
[1] Univ Autonoma Madrid, Escuela Politecn Super, Video Proc & Understanding Lab, E-28049 Madrid, Spain
来源：
IMAGE AND VISION COMPUTING | 2012年 / 30卷 / 4-5期
关键词：
People detection; People tracking; Collaborative system; Video surveillance; MOTION; VIDEO; SURVEILLANCE; FEATURES; COLOR;
D O I：
10.1016/j.imavis.2012.03.005
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The main contributions of this paper covers two different aspects: people detection and tracking. A whole detection/tracking system that integrates appearance, motion and tracking information is presented. This system uses the information provided by each of the independent tasks to improve the final result of the system. The tracking information is integrated in the detection task improving the detection results and vice versa. The experimental results over an extensive and challenging video dataset point out the state of the art limitations in complex or realistic scenarios, and show that the proposed collaborative system significantly reduces these limitations and improves the results in this kind of scenarios. (C) 2012 Elsevier B.V. All rights reserved.
引用
收藏
页码：345 / 354
页数：10
相关论文
共 42 条
  • [1] Andriluka M, 2009, PROC CVPR IEEE, P1014, DOI 10.1109/CVPRW.2009.5206754
  • [2] [Anonymous], TRECV 2008 EV SURV E
  • [3] [Anonymous], P ECCV
  • [4] [Anonymous], 2008, P CVPR
  • [5] [Anonymous], 2008, P 2008 IEEE C COMP V, DOI DOI 10.1109/CVPR.2008.4587533
  • [6] [Anonymous], PROC CVPR IEEE
  • [7] [Anonymous], 2009, Tech. Rep. CMU-CS- 09-161
  • [8] [Anonymous], MITCSAILTR2008 MIT
  • [9] [Anonymous], 2005, Computer Vision and Pattern Recognition-Workshops
  • [10] Ensemble tracking
    Avidan, Shai
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2007, 29 (02) : 261 - 271
12345