A unique target representation and voting mechanism for visual tracking

Changlin Xiao, Alper YilmazICIP 2017 · OpenReview

Abstract

One of the main problems in visual tracking is how to robustly represent the target. In this paper, we propose a simple yet efficient method that provides a unique “target representation” by generating discriminative non-uniform subspaces from the feature space which we refer to as cells. Each cell is attributed with a measure that highlights how likely it describes the target or the background. In addition, we keep a codebook of spatial locations of the features which are mapped to the cell similar to that of the R-Table in generalized Hough transform. Using the uniqueness measure as weight, the target center is estimated by using a modified Hough voting scheme to address non-rigid deformations. In the experiment, we use color as the pixel's descriptor and demonstrate comparable performance on the Online Tracking Benchmark (OTB) dataset respect to the other state-of-the-art.
BibTeX
@inproceedings{xiao2017unique,
  author = {Changlin Xiao and Alper Yilmaz},
  title = {{A unique target representation and voting mechanism for visual tracking}},
  booktitle = {ICIP},
  year = {2017},
  url = {https://openreview.net/forum?id=QfBgpPZwP3},
}

Loading related content...

Figure