A large margin framework for single camera offline tracking with hybrid cues

  • Authors:

  • Bahman Yari Saeed Khanloo;Ferdinand Stefanus;Mani Ranjbar;Ze-Nian Li;Nicolas Saunier;Tarek Sayed;Greg Mori

  • Affiliations:

  • School of Computing Science, Simon Fraser University, Burnaby, BC, Canada V5A 1S6;School of Computing Science, Simon Fraser University, Burnaby, BC, Canada V5A 1S6;School of Computing Science, Simon Fraser University, Burnaby, BC, Canada V5A 1S6;School of Computing Science, Simon Fraser University, Burnaby, BC, Canada V5A 1S6;Dept. of Civil, Geological and Mining Engineering, ícole Polytechnique de Montréal, Montréal, Québec, Canada H3C 3A7;Dept. of Civil Engineering, University of British Columbia, Vancouver, BC, Canada V6T 1Z4;School of Computing Science, Simon Fraser University, Burnaby, BC, Canada V5A 1S6

  • Venue:
  • Computer Vision and Image Understanding
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

We introduce MMTrack (max-margin tracker), a single-target tracker that linearly combines constant and adaptive appearance features. We frame offline single-camera tracking as a structured output prediction task where the goal is to find a sequence of locations of the target given a video. Following recent advances in machine learning, we discriminatively learn tracker parameters by first generating suitable bad trajectories and then employing a margin criterion to learn how to distinguish among ground truth trajectories and all other possibilities. Our framework for tracking is general, and can be used with a variety of features. We demonstrate a system combining a variety of appearance features and a motion model, with the parameters of these features learned jointly in a coherent learning framework. Further, taking advantage of a reliable human detector, we present a natural way of extending our tracker to a robust detection and tracking system. We apply our framework to pedestrian tracking and experimentally demonstrate the effectiveness of our method on two real-world data sets, achieving results comparable to state-of-the-art tracking systems.