ACIVS 2011: Advanced Concepts for Intelligent Vision Systems pp 471-482 | Cite as
An Intelligent Video Security System Using Object Tracking and Shape Recognition
Abstract
This paper deals with an intelligent video surveillance system using object tracking and recognition techniques. The proposed system integrates the object extraction, human recognition, face detection, object tracking, and camera control. First, the object in the video frame is extracted using the background subtraction. Then, the object region is examined whether it is human or not. For this recognition, the region-based shape descriptor, angular radial transform, is used to model the human shapes. When the object is decided as human, the face detection is optionally performed to capture the clear face images. Finally, the face or object region is tracked in the video frames, and the pan/tilt/zoom (PTZ) controllable camera also tracks the moving object. The tracking filter updates the histogram information in the object region at every frame so that the moving object is well tracked even though the poses and sizes of object are varied. Since the PTZ parameters can be transformed into camera parameters such as rotation angles and focal length, we estimate the 3-D locations of moving object with multiple PTZ camera. This paper constructs test system with multiple PTZ cameras and their communication protocol. According to the experiments, the proposed system is able to track the moving person automatically not only in the image domain but also in the real 3-D space. The proposed system improves the surveillance efficiency using the usual PTZ cameras.
Keywords
Visual surveillance PTZ camera object extraction object tracking shape recognitionPreview
Unable to display preview. Download preview PDF.
References
- 1.Valera, M., Velastin, S.: Intelligent distributed surveillance systems: A review. IEEE Proc. Vis. Image, Signal Process. 152(2), 192–204 (2005)CrossRefGoogle Scholar
- 2.Hampapur, A., et al.: Smart video surveillance: Exploring the concept of multiscale spatiotemporal tracking. IEEE Sig. Proc. Mag. 22(2), 38–51 (2005)CrossRefGoogle Scholar
- 3.Micheloni, C., Rinner, B., Foresti, G.L.: Video analysis in pan-tilt-zoom camera networks. IEEE Sig. Proc. Mag, 78–90 (September 2010)Google Scholar
- 4.Piccardi, M.: Background subtraction techniques: a review. In: IEEE International Conf. on Systems, Man and Cybernetics, pp. 3099–3104 (2004)Google Scholar
- 5.Seki, M., Wada, T., Fujiwara, H., Sumi, K.: Background subtraction based on cooccurrence of image variations. In: Proc. of CVPR 2003, vol. 2, pp. 65–72 (2003)Google Scholar
- 6.Qureshi, F.Z., Terzopoulos, D.: Planning ahead for PTZ camera assignment and handoff. In: Proc. ACM/IEEE Conf. Distributed Smart Cameras, pp. 1–8 (2009)Google Scholar
- 7.Rinner, B., Wolf, W.: Introduction to distributed smart cameras. Proc. IEEE 96(10), 1565–1575 (2008)CrossRefGoogle Scholar
- 8.Soto, C., Song, B., Roy-Chowdhury, A.: Distributed multi-target tracking in a self-configuring camera network. In: Proc. IEEE CVPR, pp. 1486–1493 (2009)Google Scholar
- 9.Yu, D., Hu, J., Yan, H.: A multiple point boundary smoothing algorithm. Pattern Recognition Letters, 657–668 (June 1998)Google Scholar
- 10.Jeannin, S.: MPEG-7 visual part of experimentation model version 9.0, in ISO/IEC JTC1/SC29/WG11/N3914 (January 2001)Google Scholar
- 11.Coeurjolly, D., Ricard, J., Baskurt, A.: Generalizations of angular radial transform for 2D and 3D shape retrieval. Pattern Recognition Letters 26(14), 2174–2186 (2005)CrossRefGoogle Scholar
- 12.Yang, M.-H., Kriegman, D.J., Ahuja, N.: Detecting faces in images: A survey. IEEE Trans. on PAMI 24(1), 34–58 (2002)CrossRefGoogle Scholar
- 13.Hsu, R.-L., Mohamed, A.-M., Jain, A.K.: Face detection in color images. IEEE Trans. on PAMI 24, 696–706 (2002)CrossRefGoogle Scholar
- 14.Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. on PAMI 24(5), 603–619 (2002)CrossRefGoogle Scholar
- 15.PELCO-D Protocol manualGoogle Scholar