Human pose estimation in unconstrained images and videos is a fundamental computer vision task. To illustrate the evolutionary path in technique, in this survey we summarize representative human pose methods in a structured taxonomy, with a particular focus on deep learning models and single-person image setting. Specifically, we examine and survey all the components of a typical human pose estimation pipeline, including data augmentation, model architecture and backbone, supervision representation, post-processing, standard datasets, evaluation metrics. To envisage the future directions, we finally discuss the key unsolved problems and potential trends for human pose estimation.
@article{arxiv.2109.10056,
title = {Single Person Pose Estimation: A Survey},
author = {Feng Zhang and Xiatian Zhu and Chen Wang},
journal= {arXiv preprint arXiv:2109.10056},
year = {2021}
}