Detection- and trajectory-level exclusion in multiple object tracking
Files
(Restricted Access)
Date
2013
Authors
Milan, A.
Schindler, K.
Roth, S.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013: pp.3682-3689
Statement of Responsibility
Anton Milan, Konrad Schindler, Stefan Roth
Conference Name
IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)
Abstract
When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be assigned at most one observation per frame, (2) in trajectory estimation, two trajectories should remain spatially separated at all times to avoid collisions. Yet, existing trackers often sidestep these important constraints. We address this using a mixed discrete-continuous conditional random field (CRF) that explicitly models both types of constraints: Exclusion between conflicting observations with super modular pairwise terms, and exclusion between trajectories by generalizing global label costs to suppress the co-occurrence of incompatible labels (trajectories). We develop an expansion move-based MAP estimation scheme that handles both non-sub modular constraints and pairwise global label costs. Furthermore, we perform a statistical analysis of ground-truth trajectories to derive appropriate CRF potentials for modeling data fidelity, target dynamics, and inter-target occlusion.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2013 IEEE