Areal-Time Object Detecting and Tracking System for Outdoor Night Surveillance
Pattern Recognition 41 (2008) 432 – 444 www.elsevier.com/locate/pr A real-time object detecting and tracking system for outdoor night surveillance Kaiqi Huang a , ∗ , Liangsheng Wang a , Tieniu Tan a , Steve Maybank b a National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China b School of Computer Science and Information Systems, Birkbeck College, Malet Street, London WC1E 7HX, UK
Received 27 April 2006; received in revised form 31 March 2007; accepted 23 May 2007
Abstract
Autonomous video surveillance and monitoring has a rich history. Many deployed systems are able to reliably track human motion in indoor and controlled outdoor environments. However, object detection and tracking at night remain very important problems for visual surveillance.
The objects are often distant, small and their signatures have low contrast against the background. Traditional methods based on the analysis of the difference between successive frames and a background frame will do not work. In this paper, a novel real time object detection algorithm is proposed for night-time visual surveillance. The algorithm is based on contrast analysis. In the first stage, the contrast in local change over time is used to detect potential moving objects. Then motion prediction and spatial nearest neighbor data association are used to suppress false alarms. Experiments on real scenes show that the algorithm is effective for night-time object detection and tracking.
2007 Published by Elsevier Ltd on behalf of Pattern Recognition Society.
Keywords: Visual surveillance; Night; Contrast; Detection and tracking
1. Introduction
Object detecting and tracking are important in any visionbased surveillance system. Various approaches to object detection have been proposed for surveillance, including feature-based object detection [1–4], template-based object detection [8,9] and background subtraction or inter-frame
Received 27 April 2006; received in revised form 31 March 2007; accepted 23 May 2007
Abstract
Autonomous video surveillance and monitoring has a rich history. Many deployed systems are able to reliably track human motion in indoor and controlled outdoor environments. However, object detection and tracking at night remain very important problems for visual surveillance.
The objects are often distant, small and their signatures have low contrast against the background. Traditional methods based on the analysis of the difference between successive frames and a background frame will do not work. In this paper, a novel real time object detection algorithm is proposed for night-time visual surveillance. The algorithm is based on contrast analysis. In the first stage, the contrast in local change over time is used to detect potential moving objects. Then motion prediction and spatial nearest neighbor data association are used to suppress false alarms. Experiments on real scenes show that the algorithm is effective for night-time object detection and tracking.
2007 Published by Elsevier Ltd on behalf of Pattern Recognition Society.
Keywords: Visual surveillance; Night; Contrast; Detection and tracking
1. Introduction
Object detecting and tracking are important in any visionbased surveillance system. Various approaches to object detection have been proposed for surveillance, including feature-based object detection [1–4], template-based object detection [8,9] and background subtraction or inter-frame
References: [1] D. Crandall, J. Luo, Robust color object detection using spatial-color joint probability functions, in: Proceedings of CVPR, 2004, pp [2] J. Weng, J. Ahuja, N. Huang, Matching two perspective views, PAMI 14 (8) (1992) 806–825. [4] C.G. Harris, M. Stephens, A combined corner and edge detector, Fourth Alvey Vision Conference, 1988, pp [5] C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real-time tracking, CVPR, 1999, pp [6] C.R. Wren, A. Azarbayejani, A. Pentland, Pfinder: realtime tracking of the human body, PAMI 19 (7) (1997) 780–785. (2004) 1459–1472. [8] A.K. Jain, Y. Zhong, S. Lakshmanan, Object matching using deformable templates, PAMI 18 (3) (1996) 267–278. [9] S. Sclaroff, L. Liu, Deformable shape detection and description via model based region grouping, PAMI 23 (5) (2001) 474–489. [10] D. Davies, P.L. Palmer, M. Mirmehdi, Detection and tracking of very small low contrast objects, BMVC, 1998, pp [12] S.G. Narasimhan, S.K. Nayar, Contrast restoration of weather degraded images, PAMI 25 (6) (2003) 713–724. Washington, 2004, pp. 528–535. (2004) 2013–2023. [15] E.P. Bennett, L. McMillan, Video enhancement using per-pixel virtual exposures, SIGGRAPH2005, 2005. ‘Open challenges in cognitive Vision’, Whistler, BC, Canada, December, 2003. [19] J. Kaas, C.E. Collines, The Primate Visual System, Social Science, 2003. [20] I. Haritaoglu, D. Harwood, L. Davis, W4 s: a real-time system for detecting and tracking people in 2.5D, ECCV, 1998. Thonnat, The passwords project, ICIP, IEEE, 1996, pp. 1112–1115. [23] S. Rowe, A. Blake, Statistical background modeling for tracking with a virtual camera, Proceedings of British Machine Vision Conference, 1995. University, 2000. Intelligent Industrial Automation and Soft Computing, 1999. settings, Proceedings of the IEEE, October 2001, pp. 1382–1402. Soc. Am. A 18 (2) (2001) 283–293. [29] R.M. Haralick, L.G. Shapiro, Computer and Robot Vision, vol. 1, Addison-Wesley, Reading, MA, 1992 pp [30] P.G.J. Barten, Contrast sensitivity of the Human Eye and its Effects on Image Quality, SPIE, Bellingham, Washington, 1999. [32] Y.-F. Ma, H.-J. Zhang, Detection motion object by spatial-temporal entropy, ICME, 2001, pp