A Line-of-Sight Sensor Network for Wide Area Video Surveillance: Simulation and Evaluation
Abstract
Substantial performance improvement of a wide area video surveillance network can be obtained with the addition of a Line-of-Sight sensor. The research described in this thesis shows that while the Line-of-Sight sensor cannot monitor areas with the ubiquity of video cameras alone, the combined network produces substantially fewer false alarms and superior location precision for numerous moving people than video. Recent progress in the fabrication of inexpensive, robust CMOS-based video cameras have triggered a new approach to wide area surveillance of busy areas such as modeling an airport corridor as a distributed sensor network problem. Wireless communication between these cameras and other sensors make it more practical to deploy them in an arbitrary spatial configuration to unobtrusively monitor cooperative and non-cooperative people. The computation and communication to establish image registration between the cameras grows rapidly as the number of cameras increases. Computation is required to detect people in each image, establish a correspondence between people in two or more images, compute exact 3-D positions from each corresponding pair, temporally track targets in space and time, and assimilate resultant data until thresholds have been reached to either cause an alarm or abandon further monitoring of that person. Substantial improvement can be obtained with the addition of a Line-of-Sight sensor as a location detection system to decoupling the detection, localization, and identification subtasks. That is, if the "where" can be answered by a location detection system, the "what" can be addressed by the video most effectively.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2005
- Accession Number
- ADA435251
Entities
People
- Jamie R. Morrison
Organizations
- Air Force Institute of Technology