Adaptive Surveillance: A Novel Approach to Facial Surveillance for CCTV Systems, Final Progress Report [open pdf - 950KB]
"We have developed a surveillance system that uses real-time face recognition technology to increase the utility of currently existing CCN-compatible surveillance software. The performance of the best existing surveillance system was dramatically improved by development of techniques for: (1) dynamic adjustment of video parameters in the region of the image containing a face and (2) tracking a face to acquire multiple images of it, across video frames. The outcome of this work is a state-of-the-art, automated facial recognition surveillance system capable of providing immense value to the law enforcement community. The automation of the attentionally-taxing duty of surveillance lowers overhead, and thus, frees up resources for performance of other tasks. Use of this system will allow law enforcement to perform surveillance duties to a level of efficiency and precision beyond that which is possible at present. Ultimately, fewer crimes may be perpetrated and arrests made on the basis of surveillance may lead to a greater probability of conviction."
National Criminal Justice Reference Service: http://www.ncjrs.gov