Smart video surveillance system preserving privacy

In this paper, we present a smart video surveillance system based on standard technologies and wired or wireless IP networking. The key novelty of the system is that it protects the privacy of people under surveillance. More specifically, a video analysis module detects regions of interest in the scene by change detection or face detection techniques. It is assumed that these regions contain private and sensitive information. Scrambling is then applied only to the corresponding regions. Furthermore, the amount of distortion can be controlled by restricting scrambling to some resolution levels. As a result, the scene remains visible, but privacy-sensitive information is unidentifiable. The scrambling is controlled by a private encryption key which is kept under control of legal authorities. The latter are therefore the only ones who can grant authorization to unlock the protection and view the whole scene. Therefore, this system successfully addresses the loss of privacy issue associated with video surveillance.

[1]  Sharath Pankanti,et al.  Blinkering Surveillance: Enabling Video Privacy through Computer Vision , 2004 .

[2]  Rainer Lienhart,et al.  Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection , 2003, DAGM-Symposium.

[3]  Adi Shamir,et al.  A method for obtaining digital signatures and public-key cryptosystems , 1978, CACM.

[4]  Mohan Trivedi,et al.  The networked sensor tapestry (NeST): a privacy enhanced software architecture for interactive analysis of data in video-sensor networks , 2004, VSSN '04.

[5]  L. Sweeney,et al.  Preserving Privacy by De-identifying Facial Images , 2003 .

[6]  Lisa M. Brown,et al.  Smart surveillance: applications, technologies and implications , 2003, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint.

[7]  Touradj Ebrahimi,et al.  The JPEG 2000 still image compression standard , 2001, IEEE Signal Process. Mag..

[8]  Frederic Dufaux,et al.  JPWL: JPEG 2000 for wireless applications , 2004, SPIE Optics + Photonics.

[9]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  Frederic Dufaux,et al.  JPSEC for secure imaging in JPEG 2000 , 2004, SPIE Optics + Photonics.

[11]  Frederic Dufaux,et al.  Video surveillance using JPEG 2000 , 2004, SPIE Optics + Photonics.