Multi-Pose Multi-Target Tracking for Activity Understanding
Abstract
We evaluate the performance of a widely used tracking-by-detection and data association multi-target tracking pipeline applied to an activity-rich video dataset. In contrast to traditional work on multi-target pedestrian tracking where people are largely assumed to be upright, we use an activity-rich dataset that includes a wide range of body poses derived from actions such as picking up an object, riding a bike, digging with a shovel, and sitting down. For each step of the tracking pipeline, we identify key limitations and offer practical modifications that enable robust multi-target tracking over a range of activities. We show that the use of multiple posture-specific detectors and an appearance-based data association post-processing step can generate non-fragmented trajectories essential for holistic activity understanding.
Cite
Text
Izadinia et al. "Multi-Pose Multi-Target Tracking for Activity Understanding." IEEE/CVF Winter Conference on Applications of Computer Vision, 2013. doi:10.1109/WACV.2013.6475044Markdown
[Izadinia et al. "Multi-Pose Multi-Target Tracking for Activity Understanding." IEEE/CVF Winter Conference on Applications of Computer Vision, 2013.](https://mlanthology.org/wacv/2013/izadinia2013wacv-multi/) doi:10.1109/WACV.2013.6475044BibTeX
@inproceedings{izadinia2013wacv-multi,
title = {{Multi-Pose Multi-Target Tracking for Activity Understanding}},
author = {Izadinia, Hamid and Ramakrishna, Varun and Kitani, Kris M. and Huber, Daniel},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2013},
pages = {385-390},
doi = {10.1109/WACV.2013.6475044},
url = {https://mlanthology.org/wacv/2013/izadinia2013wacv-multi/}
}