Title :
Adaptive Target Detection and Matching for a Pedestrian Tracking System
Author :
Wan, Meng ; Hervé, Jean-Yves
Author_Institution :
Univ. of Rhode Island, Kingston
Abstract :
We present a 3D tracking system for detecting and tracking multiple targets. An extended Kalman Filter (EKF) is used to maintain each target´s 3D state and provide location predictions to the pattern matchers whose task it is to follow the targets in images. An adaptive background modeling algorithm is used together with the tracking process to detect moving objects in complex environments. We propose a warping-based pattern matching approach to deal with object deformation during tracking. We present examples of results of our tracker for outdoor scenes.
Keywords :
Kalman filters; object detection; pattern matching; target tracking; adaptive background modeling algorithm; adaptive target detection; extended Kalman filter; moving object detection; pedestrian tracking system; warping-based pattern matching approach; Cameras; Computer science; Context modeling; Humans; Layout; Object detection; Pattern matching; Statistics; Target tracking; Visualization;
Conference_Titel :
Systems, Man and Cybernetics, 2006. SMC '06. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
1-4244-0099-6
Electronic_ISBN :
1-4244-0100-3
DOI :
10.1109/ICSMC.2006.385129