Occlusion Geodesics for Online Multi-object Tracking
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1306-1313
- https://doi.org/10.1109/cvpr.2014.170
Abstract
Robust multi-object tracking-by-detection requires the correct assignment of noisy detection results to object trajectories. We address this problem by proposing an online approach based on the observation that object detectors primarily fail if objects are significantly occluded. In contrast to most existing work, we only rely on geometric information to efficiently overcome detection failures. In particular, we exploit the spatio-temporal evolution of occlusion regions, detector reliability, and target motion prediction to robustly handle missed detections. In combination with a conservative association scheme for visible objects, this allows for real-time tracking of multiple objects from a single static camera, even in complex scenarios. Our evaluations on publicly available multi-object tracking benchmark datasets demonstrate favorable performance compared to the state-of-the-art in online and offline multi-object tracking.Keywords
This publication has 28 references indexed in Scilit:
- Hypergraphs for Joint Multi-view Reconstruction and Multi-object TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Online Motion Agreement TrackingPublished by British Machine Vision Association and Society for Pattern Recognition ,2013
- Globally optimal solution to multi-object tracking with merged measurementsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Who are you with and where are you going?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- PETS2009: Dataset and challengePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Multicamera People Tracking with a Probabilistic Occupancy MapIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part DetectorsInternational Journal of Computer Vision, 2007
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Maintaining multimodality through mixture trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Sonar tracking of multiple targets using joint probabilistic data associationIEEE Journal of Oceanic Engineering, 1983