English

An Improved Baseline Framework for Pose Estimation Challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop

Computer Vision and Pattern Recognition 2023-03-14 v1

Abstract

This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop. In this challenge, we aim to estimate human poses from in-the-wild stitched panoramic images. Our method is built based on Faster R-CNN for human detection, and HRNet for human pose estimation. We describe technical details for the JRDB-Pose dataset, together with some experimental results. In the competition, we achieved 0.303 OSPAIOU\text{OSPA}_{\text{IOU}} and 64.047\% AP0.5\text{AP}_{\text{0.5}} on the test set of JRDB-Pose.

Keywords

Cite

@article{arxiv.2303.07141,
  title  = {An Improved Baseline Framework for Pose Estimation Challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop},
  author = {Jiajun Fu and Yonghao Dang and Ruoqi Yin and Shaojie Zhang and Feng Zhou and Wending Zhao and Jianqin Yin},
  journal= {arXiv preprint arXiv:2303.07141},
  year   = {2023}
}
R2 v1 2026-06-28T09:14:12.181Z