Shadow Detection for Increased Accuracy of Privacy Enhancing Methods in Video Surveillance Edge Devices

Shadow detection is still considered as one of the potential challenges for intelligent automated video surveillance systems. A pre requisite for reliable and accurate detection and tracking is the correct shadow detection and classification. In such a landscape of conditions, privacy issues add more and more complexity and require reliable shadow detection. In this work the intertwining between security, accuracy, reliability and privacy is analyzed and, accordingly, a novel architecture for Privacy Enhancing Video Surveillance (PEVS) is introduced. Shadow detection and masking are dealt with through the combination of two different approaches simultaneously. This results in a unique privacy enhancement, without affecting security. Subsequently, the methodology was employed successfully in a large-scale wireless video surveillance system; privacy relevant information was stored and encrypted on the unit, without transferring it over an un-trusted network.

Authors:

• F. Matusek
• G. Pujolle
• R. Reda

Keywords:

• Video Surveillance
• Intelligent Video Surveillance
• Physical Security
• WSSU
• Privacy
• Shadow Detection.

References:

[1] F. Matusek, S. Sutor, K. Kraus, F. Kruse and R. Reda, NIVSS: A Nearly
Indestructible Video Surveillance System, The Third International
Conference on Internet Monitoring and Protection, Bucharest, July 2008.
[2] A. Prati, I. Mikic, M.M. Trivedi and R. Cucchiara. Detecting Moving
Shadows: Algorithms and Evaluation. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 25: 918 - 923, July 2003.
[3] A. Prati, I. Mikic, R. Cucchiara and M.M. Trivedi. Comparative
Evaluation of Moving Shadow Detection Algorithms. Proceedings of
3rd Workshop on Empirical Evaluation in Computer Vision (in
conjunction with CVPR 2001), December 2001.
[4] T. Horprasert, D. Harwood and L.S. Davis. A statistical approach for
real-time robust background subtraction and shadow detection.
Proceedings of IEEE ICCV'99 FRAME-RATE Workshop, 1999.
[5] S. Sutor, F. Matusek, and R. Reda, "WSSU: Wireless Self-Contained
Surveillance Unit; An Ad-Hoc Video Surveillance System", in Press,
presented at The Fourth Advanced International Conference on
Telecommunications, Athens, June, 2008.
[6] F. Matusek and R. Reda, "Efficient and Secure Storage of Privacy
Enhanced Video Surveillance Data in Intelligent Video Surveillance
Systems", to be presented at the International Symposium on Computer
and Information Sciences, October 2008.
[7] F. Matusek and R Reda, VSLC: Video Surveillance Network Control,
Mobile Video Surveillance Local Control Engineering and Applications
to be presented at IEEE, IFIP Wireless Days Conference 2008.
[8] S. Nadimi and B. Bhanu. Physical models for moving shadow and object
detection in video. IEEE Transactions on Pattern Analysis and Machine
Intelligence, 26:1079 - 1087, August 2004.
[9] Y. Cheng, "Mean Shift, Mode Seeking and Clustering," IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 17, pp.
790-799, 1995.
[10] P. Viola, and Michael Jones. "Rapid Object Detection using a Boosted
Cascade of Simple Features," cvpr, p. 511, IEEE Computer Society
Conference on Computer Vision and Pattern Recognition (CVPR'01) -
Volume 1, 2001.
[11] C. Stauffer and E. Grimson. Adaptive background mixture models for
real-time tracking. IEEE Transactions on Pattern Analysis and Machine
Intelligence, 22:747 - 757, August 2000.