Multi-Person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network
Abstract
Multi-person pose estimation is a fundamental yet challenging task in machine learning. In parallel, recent development of pose estimation has increased interests on pose tracking in recent years. In this work, we propose an efficient and powerful method to locate and track human pose. Our proposed method builds upon the state-of-the-art single person pose estimation system (Cascaded Pyramid Network), and adopts the IOU-tracker module to identify the people in the wild. We conduct experiments on the released multi-person video pose estimation benchmark (PoseTrack2018) to validate the effectiveness of our network. Our model achieves an accuracy of 80.9% on the validation and 77.1% on the test set using the Mean Average Precision (MAP) metric, an accuracy of 64.0% on the validation and 57.4% on the test set using the Multi-Object Tracking Accuracy (MOTA) metric.
Cite
Text
Yu et al. "Multi-Person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11012-3_19Markdown
[Yu et al. "Multi-Person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/yu2018eccvw-multiperson/) doi:10.1007/978-3-030-11012-3_19BibTeX
@inproceedings{yu2018eccvw-multiperson,
title = {{Multi-Person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network}},
author = {Yu, Dongdong and Su, Kai and Sun, Jia and Wang, Changhu},
booktitle = {European Conference on Computer Vision Workshops},
year = {2018},
pages = {221-226},
doi = {10.1007/978-3-030-11012-3_19},
url = {https://mlanthology.org/eccvw/2018/yu2018eccvw-multiperson/}
}