Visual Recognition of Human and Vehicle Motion for Enhanced Security

 Tieniu Tan

 National Lab of Pattern Recognition (NLPR)

CAS Institute of Automation (CASIA)

Beijing 100080, China

Abstract

In this talk, we will report some of our recent work in image and video understanding. In particular, we will describe algorithms and systems for the automatic interpretation of human and vehicle motion seen in surveillance videos, where automatic interpretation involves object motion detection, object recognition and localization, object motion tracking and the analysis of object motion trajectories in order to detect and alert abnormal behaviors.