Skip to Main content Skip to Navigation
Conference papers

On Pairwise Cost for Multi-Object Network Flow Tracking

Visesh Chari 1, 2 Simon Lacoste-Julien 2, 3, 4 Ivan Laptev 2, 1 Josef Sivic 2, 1
1 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique - ENS Paris
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Multi-object tracking has been recently approached with the min-cost network flow optimization techniques. Such methods simultaneously resolve multiple object tracks in a video and enable modeling of dependencies among tracks. Min-cost network flow methods also fit well within the "tracking-by-detection" paradigm where object trajectories are obtained by connecting per-frame outputs of an object detector. Object detectors, however, often fail due to occlusions and clutter in the video. To cope with such situations, we propose to add pairwise costs to the min-cost network flow framework. While integer solutions to such a problem become NP-hard, we design a convex relaxation solution with an efficient rounding heuristic which empirically gives certificates of small suboptimality. We evaluate two particular types of pairwise costs and demonstrate improvements over recent tracking methods in real-world video sequences.
Complete list of metadata
Contributor : Simon Lacoste-Julien Connect in order to contact the contributor
Submitted on : Wednesday, January 28, 2015 - 4:31:51 PM
Last modification on : Friday, January 21, 2022 - 3:22:31 AM

Links full text


  • HAL Id : hal-01110678, version 1
  • ARXIV : 1408.3304



Visesh Chari, Simon Lacoste-Julien, Ivan Laptev, Josef Sivic. On Pairwise Cost for Multi-Object Network Flow Tracking. CVPR 2015 - 28th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. ⟨hal-01110678⟩



Les métriques sont temporairement indisponibles