Lim, Ser Nam
“This document is the final report for the NIJ research program “Advanced Behavior Recognition in Crowded Environments”. The goal of this program is to increase the situational awareness in law-enforcement and correctional settings and reliably detect and prevent activities indicative of disorderly conduct and criminal behavior. Examples include fights, riots, the formation of drug markets, and gang activities. A particular emphasis of this program is to develop robust probabilistic event modeling framework that takes the uncertainty of low-level image evidence into consideration. In addition, our technology aims for user friendly interaction to the law-enforcement end users by developing event explanation and scenario modeling GUI [graphical user interface] … Overall this program has led to the development of a wide range of intelligent video capabilities that are highly relevant to law enforcement and corrections. The developed technology can help law enforcement detect many different types of events and alert operators in many cases about the onset of an event – enabling early detection and possibly prevention of critical events. The system will also allow law enforcement gain insight into the ways that people behave and interact.” (p. 1).