Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians
Abstract
Although ‘tracking-by-detection’ is a popular approach when reliable object detectors are available, missed detections remain a difficult hurdle to overcome. We present a hybrid stochastic/deterministic optimization scheme that uses RJMCMC to perform stochastic search over the space of detection configurations, interleaved with deterministic computation of the optimal multi-frame data association for each proposed detection hypothesis. Since object trajectories do not need to be estimated directly by the sampler, our approach is more efficient than traditional MCMCDA techniques. Moreover, our holistic formulation is able to generate longer, more reliable trajectories than baseline tracking-by-detection approaches in challenging multi-target scenarios.
Cite
Text
Collins and Carr. "Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10605-2_20Markdown
[Collins and Carr. "Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/collins2014eccv-hybrid/) doi:10.1007/978-3-319-10605-2_20BibTeX
@inproceedings{collins2014eccv-hybrid,
title = {{Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians}},
author = {Collins, Robert T. and Carr, Peter},
booktitle = {European Conference on Computer Vision},
year = {2014},
pages = {298-313},
doi = {10.1007/978-3-319-10605-2_20},
url = {https://mlanthology.org/eccv/2014/collins2014eccv-hybrid/}
}