Inferring Tracklets for Multi-Object Tracking
Abstract
Recent work on multi-object tracking has shown the promise of tracklet-based methods. In this work we present a method which infers tracklets then groups them into tracks. It overcomes some of the disadvantages of existing methods, such as the use of heuristics or non-realistic constraints. The main idea is to formulate the data association problem as inference in a set of Bayesian networks. This avoids exhaustive evaluation of data association hypotheses, provides a confidence estimate of the solution, and handles split-merge observations. Consistency of motion and appearance is the driving force behind finding the MAP data association estimate. The computed tracklets are then used in a complete multi-object tracking algorithm, which is evaluated on a vehicle tracking task in an aerial surveillance context. Very good performance is achieved on challenging video sequences. Track fragmentation is nearly non-existent, and false alarm rates are low.
Cite
Text
Prokaj et al. "Inferring Tracklets for Multi-Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011. doi:10.1109/CVPRW.2011.5981753Markdown
[Prokaj et al. "Inferring Tracklets for Multi-Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011.](https://mlanthology.org/cvprw/2011/prokaj2011cvprw-inferring/) doi:10.1109/CVPRW.2011.5981753BibTeX
@inproceedings{prokaj2011cvprw-inferring,
title = {{Inferring Tracklets for Multi-Object Tracking}},
author = {Prokaj, Jan and Duchaineau, M. and Medioni, Gérard G.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2011},
pages = {37-44},
doi = {10.1109/CVPRW.2011.5981753},
url = {https://mlanthology.org/cvprw/2011/prokaj2011cvprw-inferring/}
}