Data association and occlusion handling for vision-based people tracking by mobile robots

被引:26
作者
Cielniak, Grzegorz [1 ]
Duckett, Tom [1 ]
Lilienthal, Achim J. [2 ]
机构
[1] Lincoln Univ, Sch Comp Sci, Lincoln, Lincs LN6 7TS, England
[2] Univ Orebro, Ctr Appl Autonomous Sensor Syst, SE-70182 Orebro, Sweden
关键词
AdaBoost; Occlusion detection; Thermal vision; Colour vision; Bayesian estimation;
D O I
10.1016/j.robot.2010.02.004
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets. (C) 2010 Elsevier B.V. All rights reserved.
引用
收藏
页码:435 / 443
页数:9
相关论文
共 37 条
  • [1] Andriluka Micha., 2009, Robocuprescue 2009-robot league team darmstadt rescue robot team (germany)
  • [2] [Anonymous], 2005, WORKSH EMP EV METH C
  • [3] [Anonymous], 2004, Beyond the Kalman Filter: Particle Filters for Tracking Applications
  • [4] ARGYROS AA, 2004, P EUR C COMP VIS ECC, V3, P368
  • [5] Pedestrian detection in infrared images
    Bertozzi, M
    Broggi, A
    Grisleri, P
    Graf, T
    Meinecke, M
    [J]. IEEE IV2003: INTELLIGENT VEHICLES SYMPOSIUM, PROCEEDINGS, 2003, : 662 - 667
  • [6] Face tracking and hand gesture recognition for human-robot interaction
    Brèthes, L
    Menezes, P
    Lerasle, F
    Hayet, J
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS, 2004, : 1901 - 1906
  • [7] CIELNIAK G, 2007, P IEEE RSJ INT C INT, P3436
  • [8] CIELNIAK G, 2007, THESIS OREBRO U
  • [9] DOERMANN D, 2000, P INT C PATT REC, V4, P4167
  • [10] ELGAMMAL A, 2001, P INT C COMP VIS VAN