Omni-directional visual surveillance

被引:57
作者
Boult, TE
Gao, X
Micheals, R
Eckmann, M
机构
[1] Univ Colorado, Colorado Springs, CO 80933 USA
[2] Natl Inst Stand & Technol, Gaithersburg, MD 20899 USA
[3] Lehigh Univ, Dept Comp Sci & Engn, Bethlehem, PA 18015 USA
关键词
detection; tracking; background adaptation; real-time; frame-rate; hysteresis; connected-components; quasi-connected-components; omni-directional video;
D O I
10.1016/j.imavis.2003.09.005
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Perimeter security generally requires watching areas that afford trespassers reasonable cover and concealment. By definition, such 'interesting' areas have limited visibility distance. Furthermore, targets of interest generally attempt to conceal themselves within the cover, sometimes adding camouflage to further reduce their visibility. Such targets are only visible while in motion. The combined result of limited visibility and target visibility severely reduces the usefulness of any approach using a standard Pan/Tilt/Zoom (PTZ) camera. As a result, these situations call for a very sensitive system with a wide field of view, and are a natural application for Omni-directional Video Surveillance and Monitoring. This paper describes a frame-rate, low-power, omni-directional tracking system (LOTS). The paper discusses related background work including resolution issues in omni-directional imaging. One of the novel system component details is quasi-connected-components (QCC). QCC combines gap filling, thresholding-with-hysteresis (TWH) and a novel region merging/cleaning approach. The multi-background modeling and dynamic thresholding make an ideal approach for difficult situations like outdoor tracking in high clutter. The paper also describes target geolocation and issues in the system user interface. The single viewpoint property of the omni-directional imaging system used simplifies the backprojection and unwarping. We end with a summary of an external evaluation of an early form of the system and comments about recent work and field tests. (C) 2003 Elsevier B.V. All rights reserved.
引用
收藏
页码:515 / 534
页数:20
相关论文
共 60 条
[1]  
AYER A, 1994, COMPUTER ECCV STOCKH, V2, P316
[2]   The computation of optical flow [J].
Beauchemin, SS ;
Barron, JL .
ACM COMPUTING SURVEYS, 1995, 27 (03) :433-467
[3]  
BEYMER D, 1997, P IEEE C COMP VIS PA
[4]   DETECTING SMALL, MOVING-OBJECTS IN IMAGE SEQUENCES USING SEQUENTIAL HYPOTHESIS-TESTING [J].
BLOSTEIN, SD ;
HUANG, TS .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1991, 39 (07) :1611-1629
[5]  
BOGAERT M, 1996, PASSWORDS PROJECT, P1112
[6]  
BOGNER S, 1995, P IEEE SMC C, P3100
[7]  
BOULT T, 1998, P IEEE WORKSH COMP V
[8]  
BOULT T, 1996, MACHINE GRAPHICS VIS
[9]   Into the woods: Visual surveillance of noncooperative and camouflaged targets in complex outdoor settings [J].
Boult, TE ;
Micheals, RJ ;
Gao, X ;
Eckmann, M .
PROCEEDINGS OF THE IEEE, 2001, 89 (10) :1382-1402
[10]  
Boult TE, 1999, SECOND IEEE WORKSHOP ON VISUAL SURVEILLANCE (VS'99), PROCEEDINGS, P48