Learning Spatio-Temporal Topology of a Multi-Camera Network by Tracking Multiple People
This paper presents a novel approach for representing
the spatio-temporal topology of the camera network with overlapping
and non-overlapping fields of view (FOVs). The topology is
determined by tracking moving objects and establishing object
correspondence across multiple cameras. To track people successfully
in multiple camera views, we used the Merge-Split (MS) approach for
object occlusion in a single camera and the grid-based approach for
extracting the accurate object feature. In addition, we considered the
appearance of people and the transition time between entry and exit
zones for tracking objects across blind regions of multiple cameras
with non-overlapping FOVs. The main contribution of this paper is to
estimate transition times between various entry and exit zones, and to
graphically represent the camera topology as an undirected weighted
graph using the transition probabilities.
[1] Y. Choi, K. Kim, W. Cho, "Grid-Based Approach for Detecting Head and
Hand Regions," International Conference on Intelligent Computing,
Qingdao China, August 21-24, 2007, pp. 1126-1132.
[2] J. Black, T. Ellis, and D. Makris, "Wide Area Surveillance with a
Multi-Camera Network," Proc. IDSS-04 Intelligent Distributed
Surveillance Systems, 2003, pp. 21-25.
[3] P. KaewTrakulPong and R. Bowden, "A Real-time Adaptive Visual
Surveillance System for Tracking Low Resolution Colour Targets in
Dynamically Changing Scenes," Journal of Image and Vision Computing.
Vol 21, Issue 10, Elsevier Science Ltd, 2003, pp. 913-929.
[4] J. Sturges and T. Whitfield, "Locating Basic Colour in the Munsell
Space," Colour Research and Application, 1995, pp. 364-376.
[5] Q. Cai and J. Agrarian, "Tracking Human Motion using Multiple
Cameras," Proc. International Conference on Pattern Recognition, 1996,
pp. 67-72.
[6] P. Kelly, A. Katkere, D. Kuramura, S. Moezzi, and S. Chatterjee, "An
Architecture for Multiple Perspective Interactive Video," Proc. of the 3rd
ACE International Conference on Multimedia, 1995, pp. 201-212.
[7] G. Welch and G. Bishop, "An Introduction to the Kalman Kilter,"
Technical Report 95-041,University of North Carolina at Chapel Hill,
1995.
[8] I. Haritaoglu, D. Harwood, L. Davis, "W4:Who, When, Where, What: A
Real Time System for Detecting and Tracking People," Third
International Conference on Automatic Face and Gesture, 1998.
[9] I. Haritaoglu, D. Harwood, and L. S. Davis, "W4S: A realtime system for
detecting and tracking people in 2 1/2D," 5th European Conference on
Computer Vision, Freiburg, Germany, 1998.
[10] V. Kettnaker, R. Zabih, "Counting People from multiple cameras," in
IEEE ICMCS, Florence, Italy, 1999, pp. 267-271.
[11] T. Huang and S. Russell, "Object Identification in a Bayesian Context,"
Proc. International Joint Conference on Artificial Intelligence (IJCAI-97),
Nagoya, Japan, 1997, pp. 1276-1283.
[12] Q. Cai and J.K. Aggarwal, "Automatic Tracking of Human Motion in
Indoor Scenes Across Multiple Synchronized video Streams," 6th
International conference on Computer Vision, Bombay, India, 1998, pp.
356-362.
[13] O. Javed, Z. Rasheed, K. Shafique, and M. Shah. "Tracking Across
Multiple Cameras with Disjoint Views". Proc. IEEE International
Conference on Computer Vision, 2003, pp. 952-957.
[14] A. Dick and M. Brooks, "A Stochastic Approach to Tracking Objects
Across Multiple Cameras," Australian Conference on Artificial
Intelligence, 2004, pp. 160-170.
[15] T. J. Ellis, D. Makris, and J. Black, "Learning a multi-camera topology,"
In Joint IEEE Workshop on Visual Surveillance and Performance
Evaluation of Tracking and Surveillance (VS-PETS), 2003, pp. 165-171.
[16] C. Stauffer, "Learning to track objects through unobserved regions," In
IEEE Computer Society Workshop on Motion and Video Computing,
2005, pp. 96-102.
[17] K. Tieu, G. Dalley, and W. Grimson, "Inference of nonoverlapping
camera network topology by measuring statistical dependence," In Proc.
IEEE International Conference on Computer Vision, 2005, pp.
1842-1849.
[18] A. Gilbert, R. Bowden, "Tracking Objects Across Cameras by
Incrementally Learning Inter-camera Colour Calibration and Patterns of
Activity," In Proc European Conference Computer Vision, 2006, pp.
125-136.
[19] Intel Open Source Computer Vision Library, URL
http://sourceforge.net/projects/opencvlibrary/
[1] Y. Choi, K. Kim, W. Cho, "Grid-Based Approach for Detecting Head and
Hand Regions," International Conference on Intelligent Computing,
Qingdao China, August 21-24, 2007, pp. 1126-1132.
[2] J. Black, T. Ellis, and D. Makris, "Wide Area Surveillance with a
Multi-Camera Network," Proc. IDSS-04 Intelligent Distributed
Surveillance Systems, 2003, pp. 21-25.
[3] P. KaewTrakulPong and R. Bowden, "A Real-time Adaptive Visual
Surveillance System for Tracking Low Resolution Colour Targets in
Dynamically Changing Scenes," Journal of Image and Vision Computing.
Vol 21, Issue 10, Elsevier Science Ltd, 2003, pp. 913-929.
[4] J. Sturges and T. Whitfield, "Locating Basic Colour in the Munsell
Space," Colour Research and Application, 1995, pp. 364-376.
[5] Q. Cai and J. Agrarian, "Tracking Human Motion using Multiple
Cameras," Proc. International Conference on Pattern Recognition, 1996,
pp. 67-72.
[6] P. Kelly, A. Katkere, D. Kuramura, S. Moezzi, and S. Chatterjee, "An
Architecture for Multiple Perspective Interactive Video," Proc. of the 3rd
ACE International Conference on Multimedia, 1995, pp. 201-212.
[7] G. Welch and G. Bishop, "An Introduction to the Kalman Kilter,"
Technical Report 95-041,University of North Carolina at Chapel Hill,
1995.
[8] I. Haritaoglu, D. Harwood, L. Davis, "W4:Who, When, Where, What: A
Real Time System for Detecting and Tracking People," Third
International Conference on Automatic Face and Gesture, 1998.
[9] I. Haritaoglu, D. Harwood, and L. S. Davis, "W4S: A realtime system for
detecting and tracking people in 2 1/2D," 5th European Conference on
Computer Vision, Freiburg, Germany, 1998.
[10] V. Kettnaker, R. Zabih, "Counting People from multiple cameras," in
IEEE ICMCS, Florence, Italy, 1999, pp. 267-271.
[11] T. Huang and S. Russell, "Object Identification in a Bayesian Context,"
Proc. International Joint Conference on Artificial Intelligence (IJCAI-97),
Nagoya, Japan, 1997, pp. 1276-1283.
[12] Q. Cai and J.K. Aggarwal, "Automatic Tracking of Human Motion in
Indoor Scenes Across Multiple Synchronized video Streams," 6th
International conference on Computer Vision, Bombay, India, 1998, pp.
356-362.
[13] O. Javed, Z. Rasheed, K. Shafique, and M. Shah. "Tracking Across
Multiple Cameras with Disjoint Views". Proc. IEEE International
Conference on Computer Vision, 2003, pp. 952-957.
[14] A. Dick and M. Brooks, "A Stochastic Approach to Tracking Objects
Across Multiple Cameras," Australian Conference on Artificial
Intelligence, 2004, pp. 160-170.
[15] T. J. Ellis, D. Makris, and J. Black, "Learning a multi-camera topology,"
In Joint IEEE Workshop on Visual Surveillance and Performance
Evaluation of Tracking and Surveillance (VS-PETS), 2003, pp. 165-171.
[16] C. Stauffer, "Learning to track objects through unobserved regions," In
IEEE Computer Society Workshop on Motion and Video Computing,
2005, pp. 96-102.
[17] K. Tieu, G. Dalley, and W. Grimson, "Inference of nonoverlapping
camera network topology by measuring statistical dependence," In Proc.
IEEE International Conference on Computer Vision, 2005, pp.
1842-1849.
[18] A. Gilbert, R. Bowden, "Tracking Objects Across Cameras by
Incrementally Learning Inter-camera Colour Calibration and Patterns of
Activity," In Proc European Conference Computer Vision, 2006, pp.
125-136.
[19] Intel Open Source Computer Vision Library, URL
http://sourceforge.net/projects/opencvlibrary/
@article{"International Journal of Information, Control and Computer Sciences:56875", author = "Yunyoung Nam and Junghun Ryu and Yoo-Joo Choi and We-Duke Cho", title = "Learning Spatio-Temporal Topology of a Multi-Camera Network by Tracking Multiple People", abstract = "This paper presents a novel approach for representing
the spatio-temporal topology of the camera network with overlapping
and non-overlapping fields of view (FOVs). The topology is
determined by tracking moving objects and establishing object
correspondence across multiple cameras. To track people successfully
in multiple camera views, we used the Merge-Split (MS) approach for
object occlusion in a single camera and the grid-based approach for
extracting the accurate object feature. In addition, we considered the
appearance of people and the transition time between entry and exit
zones for tracking objects across blind regions of multiple cameras
with non-overlapping FOVs. The main contribution of this paper is to
estimate transition times between various entry and exit zones, and to
graphically represent the camera topology as an undirected weighted
graph using the transition probabilities.", keywords = "Surveillance, multiple camera, people tracking,
topology.", volume = "1", number = "6", pages = "1675-6", }
