Learning semantic scene models from observing activity in visual surveillance

被引:170
作者
Makris, D [1 ]
Ellis, T [1 ]
机构
[1] Kingston Univ, Kingston upon Thames KT1 2EE, Surrey, England
来源
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2005年 / 35卷 / 03期
基金
英国工程与自然科学研究理事会;
关键词
motion analysis; site security monitoring; TV surveillance systems; unsupervised learning;
D O I
10.1109/TSMCB.2005.846652
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 considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to an identifiable activity in each region, such as entry/exit zones, junctions, paths, and stop zones. We present several unsupervised methods that learn these scene elements and present results that show the efficiency of our approach. Finally, we describe how the models can be used to support the interpretation of moving objects in a visual surveillance environment.
引用
收藏
页码:397 / 408
页数:12
相关论文
共 26 条
  • [1] Black J, 2002, IEEE WORKSHOP ON MOTION AND VIDEO COMPUTING (MOTION 2002), PROCEEDINGS, P169, DOI 10.1109/MOTION.2002.1182230
  • [2] BLACK J, 2004, IEEE INT C MULT EXP, V3, P1571
  • [3] BUXTON H, 2002, EUR C COMP VIS WORKS, P77
  • [4] CUPILLARD F, 2003, IEE SEM INT DISTR SU
  • [5] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM
    DEMPSTER, AP
    LAIRD, NM
    RUBIN, DB
    [J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01): : 1 - 38
  • [6] FERNYHOUGH JH, 1996, GENERATION SEMANTIC, P475
  • [7] Using adaptive tracking to classify and monitor activities in a site
    Grimson, WEL
    Stauffer, C
    Romano, R
    Lee, L
    [J]. 1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, : 22 - 29
  • [8] HANSON AR, 1988, P ADV COMPUTER VISIO, V1, P1
  • [9] W4:: Real-time surveillance of people and their activities
    Haritaoglu, I
    Harwood, D
    Davis, LS
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) : 809 - 830
  • [10] HOWARTH RJ, 1992, P 10 EUR C AI WIL NE, P785