On Pairwise Costs for Network Flow Multi-Object Tracking

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.

  • Visesh Chari
  • Simon Lacoste-Julien
  • Ivan Laptev
  • Josef Sivic

PDF [ArXiv] [CV Foundation] [Supplementary Material]

    author      = "Chari, Visesh and Lacoste-Julien, Simon and Laptev, Ivan and Sivic, Josef",
    title       = "On Pairwise Costs for Network Flow Multi-Object Tracking",
    booktitle   = "Proc. CVPR",
    year        = "2015"
This research was supported in part by the projects FluidTracks, EIT ICT Labs, Google research award, ERC grant Activia (no. 307574) and ERC grant LEAP (no. 336845). We thank Patrick Perez for discussions on the multi-target tracking evaluation.

Subpages (4): Code Copyright Dataset Videos