MULTI-VIEW IMAGE SURVEILLANCE AND TRACKING

Abstract

The work presented in this report provides a framework for object tracking using multiple camera views. The application uses several widely separated overlapping and non-overlapping camera views for object tracking in an outdoor environment. Multiple cameras are needed to cover large environments for monitoring activity. To track moving object successfully in multiple perspective images, one needs to establish correspondence between objects captured in multiple cameras. The system, require for tracking in multi-view environment, employs a centralised control strategy, where each intelligent camera unit transmits tracking data to a multi view-tracking server. The tracking data generated by each intelligent camera unit is stored in a central surveillance database during live operation. The data stored in a surveillance database is used to generate pseudo synthetic video sequences, which can be used for performance evaluation. For overlapping camera views the homography constraint is used...