Abstract
This paper introduces a tracking algorithm to track the multiple objects across multiple non-overlapped views. First, we track every single object in each single view and record its activity as the object-based video fragments (OVFs). By linking the related OVFs across different cameras, we may connect two OVFs across two non-overlapped views. Because of scene illumination change, blind region lingering, and objects similar appearance, we may have the problem of path misconnection and fragmentation. This paper develops the Error Path Detection Function (EPDF) and uses the augmented feature (AF) to solve those two problems.
Chapter PDF
Similar content being viewed by others
Keywords
References
Black, J., et al.: Wide Area Surveillance with a Multi-Camera Network. In: Proc. of Intelligent Distributed Surveillance Systems (2003)
Lee, L., et al.: Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame. IEEE Trans. PAMI 22(8), 758–768 (2000)
Khan, S., et al.: Consistent Labeling of Tracked Objects in Multiple Cameras with Overlapped Fields of View. IEEE Trans. PAMI (2003)
Javed, O., et al.: KNIGHTM: a real time surveillance system for multiple overlapped and non-overlapped cameras. In: ICME (2003)
Zhu, L.-J., et al.: Tracking of multiple objects across multiple cameras with overlapped and non-overlapped views. In: IEEE ISCAS (2009)
Kettnaker, V., et al.: Bayesian Multi-camera Surveillance. In: IEEE CVPR (1999)
Porikli, F., et al.: Multi-Camera Calibration, Object Tracking and Query Generation. In: IEEE ICME (2003)
Javed, O., et al.: Tracking across Multiple Cameras with Disjoint Views. In: 9th IEEE ICCV (October 2003)
Javed, O., et al.: Appearance modeling for tracking in multiple non-overlapped cameras. In: IEEE CVPR 2005, vol. 2, pp. 26–33 (June 2005)
Javed, O., et al.: Modeling inter-camera space–time and appearance relationships for tracking across non-overlapped views. Computer Vision and Image Understanding, 146–162 (2008)
D’Orazio, T., et al.: Color Brightness Transfer Function Evaluation for Non overlapped Multi Camera Tracking. In: ICDSC (2009)
Chen, K.W., et al.: An Adaptive Learning Method for Target Tracking across Multiple Cameras. In: IEEE CVPR 2008, pp. 1–8 (June 2008)
Dick, A., et al.: A Stochastic Approach to Tracking Objects across Multiple Cameras. In: Australian Conf. on Artificial Intelligence, pp.160–170 (2004)
Ellis, T.J., et al.: Learning a Multi-Camera Topology. In: IEEE Workshop on VS-PETS (2003)
Stauffer, C.: Learning to Track Objects through Unobserved Regions. In: IEEE Workshop on Motion and Video Computing, pp. 96–102 (January 2005)
Mehmood, M.O.: Multi-camera based Human Tracking with Non- Overlapped Fields of View. In: Int. Conf. on AICT 2009, pp. 1–6 (October 2009)
Cheng, E.D., et al.: Mitigating the Effects of Variable Illumination for Tracking across Disjoint Camera Views. In: IEEE AVSS 2006 (November 2006)
Piccardi, M., et al.: Track matching over disjoint camera views based on an incremental major color spectrum histogram. In: IEEE AVSS (2005)
Song, B., et al.: Robust Tracking in A Camera Network A Multi-Objective Optimization Framework. IEEE J. on Selected Topics in Signal Processing, 582–596 (2008)
Comaniciu, D., Meer, P.: Mean-Shift: A robust Approach toward feature space analysis. IEEE Trans. on PAMI 24(5), 603–619 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, KY., Huang, CL., Hsu, SC., Chang, IC. (2011). Multiple Objects Tracking across Multiple Non-Overlapped Views. In: Ho, YS. (eds) Advances in Image and Video Technology. PSIVT 2011. Lecture Notes in Computer Science, vol 7088. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25346-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-25346-1_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25345-4
Online ISBN: 978-3-642-25346-1
eBook Packages: Computer ScienceComputer Science (R0)