A framework of surveillance system using a PTZ camera

For enlarging the surveillance area, more and more visual surveillance systems exploit Pan Tilt Zoom (PTZ) camera. This paper proposes a framework of surveillance system which uses a single PTZ camera. The framework is divided into two phases: offline phase and inline phase. During the offline phase, camera parameters for every image are computed using SIFT features and bundle adjustment algorithm, and then the mosaic and the background model of the whole area are generated based on the camera parameters. During the inline phase, the real-time frame is projected to the correct location on the mosaic using SIFT features and bundle adjustment algorithm, and then the moving object is detected by background subtraction technical. Experiments show that the PTZ camera's parameters can be computed in time and the moving object can be detected perfectly even when the zoom value changes a lot.

[1]  James Orwell,et al.  Learning the Semantic Landscape: embedding scene knowledge in object tracking , 2005, Real Time Imaging.

[2]  Langis Gagnon,et al.  A system to automatically track humans and vehicles with a PTZ camera , 2007, SPIE Defense + Commercial Sensing.

[3]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[4]  Mongi A. Abidi,et al.  Heterogeneous Fusion of Omnidirectional and PTZ Cameras for Multiple Object Tracking , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[6]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[7]  R. Bowden,et al.  Towards automated wide area visual surveillance: tracking objects between spatially-separated, uncalibrated views , 2005 .

[8]  Mongi A. Abidi,et al.  Real-time video tracking using PTZ cameras , 2003, International Conference on Quality Control by Artificial Vision.

[9]  Yi Yao,et al.  Cooperative mapping of multiple PTZ cameras in automated surveillance systems , 2009, CVPR.

[10]  Huaiyu Zhu.  On Information and Sufficiency , 1997 .

[11]  Anand Rangarajan,et al.  A new algorithm for non-rigid point matching , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  Richard I. Hartley,et al.  Optimised KD-trees for fast image descriptor matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Alessandro Bevilacqua,et al.  A Fast and Reliable Image Mosaicing Technique with Application to Wide Area Motion Detection , 2007, ICIAR.

[14]  Philip F. McLauchlan,et al.  Image mosaicing using sequential bundle adjustment , 2002, Image Vis. Comput..

[15]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[16]  Yi Yao,et al.  Cooperative mapping of multiple PTZ cameras in automated surveillance systems , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.