Pedestrian Tracking by Associating Tracklets using Detection Residuals
- 1 January 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Due to increased interest in visual surveillance, various multiple object tracking methods have been recently proposed and applied to pedestrian tracking. However in presence of intensive inter-object occlusion and sensor gaps, most of these methods result in tracking failures. We present a two-stage multi-object tracking approach to robustly track pedestrians in such complex scenarios. We first generate high confidence partial track segments (tracklets) using a robust pedestrian detector and then associate the tracklets in a global optimization framework. Unlike the existing two-stage tracking methods, our method uses the unasso- ciated low confidence detections (residuals) between the tracklets, which improves the tracking performance. We evaluate our method on the CAVIAR dataset and show that our method performs better than state-of-the-art methods.Keywords
This publication has 5 references indexed in Scilit:
- Multi-Target Tracking - Linking Identities using Bayesian Network Inference2006
- Joint Recognition of Complex Events and Track Matching2006
- Multiple Objects Tracking with Multiple Hypotheses Graph Representation2006
- Estimating Tracking Sources and Sinks2003
- Foreground object detection from videos containing complex background2003