The networked sensor tapestry (NeST): a privacy enhanced software architecture for interactive analysis of data in video-sensor networks

ABSTRACT

This paper details the architecture of a test-bed under development for secure sharing, capture, distributed processing, and archiving of surveillance data called the Networked Sensor Tapestry (NeST). The test-bed consists of core software modules including a centralized server, client interface library, a layered XML messaging scheme. Mobile hardware clients are interfaced to the NeST using a Tiny-OS based microcontroller with sensor data collected over a 1-wire data bus. Maintaining subject privacy in video and other sensor monitoring scenarios can be imperative for the successful deployment of surveillance networks. Subject privacy is integrated into the architecture and can (if desired) operate as a buffer to the server core, denying access to identity specific information to any or all modules or operators. We introduce 3 fundamental privacy concepts: The <i>privacy buffer</i>: is a core component of the NeST server and utilizes programmable plug-in <i>privacy filters</i> operating on incoming sensor data to prevent access to or transform data to remove personally identifiable information. These privacy filters are developed and specified using a <i>privacy grammar</i> that can connect multiple low-level data filters and features to create arbitrary data-dependent privacy definitions. The utility of the architecture is demonstrated with a connection to a variety of hardware/software clients including PDA based client hardware, remote sensor interface devices, software modules for sensor data inferencing, data visualization, sensor control and data archival applications.

REFERENCES

• 1: Mohan M. Trivedi, Kohsia S. Huang, Ivana Mikic, "Dynamic Context Capture and Distributed Video Arrays for Intelligent Spaces," Accepted (January 2004) for publication in IEEE Trans. on Systems, Man, and Cybernetics, special issue on Ambient Intelligence.
• 2: Lewis Girod, Jeremy Elson, Alberto Cerpa, Thanos Stathopoulos, Nithya Ramanathan, Deborah Estrin, "EmStar: a Software Environment for Developing and Deploying Wireless Sensor Networks", Proceeding of the 2004 USENIX Technical Conference.
• 3: B. Hall, M. M. Trivedi, "A Novel Interactivity Environment for Integrated Intelligent Transprotation and Telematic Systems," 5th International IEEE Conference on Intelligent Transportation Systems, Singapore, pp. 396--401, September 3-6, 2002.
• 4: Ulrich Neumann , Suya You , Jinhui Hu , Bolan Jiang , JongWeon Lee, Augmented Virtual Environments (AVE): Dynamic Fusion of Imagery and 3D Models, Proceedings of the IEEE Virtual Reality 2003, p.61, March 22-26, 2003
• 5: Kanade, T., R. Collins, A. Lipton, P. Burt, & Wixson, L. (1998). Advances in cooperative multi-sensor video surveillance. Proc. of DARPA Image Understanding Workshop, 1, 3--24.
• 6: K. Huang, M. M. Trivedi, "Distributed Video Arrays for Tracking, Human Identification, and Activity Analysis," Proceedings of the 4th IEEE International Conference on Multimedia and Expo, Baltimore, MD, pp. 9--12, July 2003.
• 7: Henk Muller and Cliff Randell. "An Event-Driven Sensor Architecture for Low Power Wearables". In: ICSE 2000, Workshop on Software Engineering for Wearable and Pervasive Computing, pages 39--41. ACM/IEEE, June 2000
• 8: Jason Hill , Robert Szewczyk , Alec Woo , Seth Hollar , David Culler , Kristofer Pister, System architecture directions for networked sensors, Proceedings of the ninth international conference on Architectural support for programming languages and operating systems, p.93-104, November 2000, Cambridge, Massachusetts, United States
• 9: J. E. Boyd , E. Hunter , P. H. Kelly , L.-C. Tai , C. B. Phillips , R. C. Jain, MPI-Video Infrastructure for Dynamic Environments, Proceedings of the IEEE International Conference on Multimedia Computing and Systems, p.249, June 28-July 01, 1998 [doi>10.1109/MMCS.1998.693651]
• 10: W. J. Kaiser, G.J. Pottie, M. Srivastava, G.S. Sukhatme, J. Villasenor, and D. Estrin "Networked Infomechanical Systems (NIMS) for Ambient Intelligence", in CENS Technical Report #31, December 5 2003.
• 11: V.A. Kottapalli, A.S. Kiremidjian, J.P. Lynch, E. Carryer, T.W. Kenny, K.H. Law, Y. Lei, "Two-tiered wireless sensor network architecture for structural health monitoring", SPIE's 10th Annual International Symposium on Smart Structures and Materials, San Diego, CA, USA, March 2-6, 2003.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.4 Systems and Software

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.4 Systems and Software
          Subjects: Distributed systems; Information networks

General Terms:
Design, Experimentation, Security

Keywords:
privacy, surveillance architecture, video-sensor networks