Object tracking via online metric learning

Yang Cong, Junsong Yuan, Yandong Tang

Abstract

By considering visual tracking as a similarity matching problem, we propose a self-supervised tracking method that incorporates adaptive metric learning and semi-supervised learning into the framework of object tracking. For object representation, the spatial-pyramid structure is applied by fusing both the shape and texture cues as descriptors. A metric learner is adaptively trained online to best distinguish the foreground object and background, and a new bi-linear graph is defined accordingly to propagate the label of each sample. Then high-confident samples are collected to self-update the model to handle large-scale issue. Experiments on the benchmark dataset and comparisons with the state-of-the-art methods validate the advantages of our algorithm.
BibTeX
@inproceedings{cong2012object,
  author = {Yang Cong and Junsong Yuan and Yandong Tang},
  title = {{Object tracking via online metric learning}},
  booktitle = {ICIP},
  year = {2012},
  doi = {10.1109/icip.2012.6466884},
}

Loading related content...

Figure