Vision-Based Human Pose Estimation via Deep Learning: A Survey

TL;DR

This survey reviews recent deep learning methods for vision-based human pose estimation, covering 2-D and 3-D approaches, challenges, trends, and future directions to guide both beginners and experts.

Contribution

It provides a comprehensive, up-to-date overview of deep learning techniques in human pose estimation, including applications, challenges, and research trends.

Findings

Deep learning has achieved state-of-the-art performance in HPE.

The survey highlights key challenges and future research directions.

Bibliometric analysis reveals evolving trends in HPE research.

Abstract

Human pose estimation (HPE) has attracted a significant amount of attention from the computer vision community in the past decades. Moreover, HPE has been applied to various domains, such as human-computer interaction, sports analysis, and human tracking via images and videos. Recently, deep learning-based approaches have shown state-of-the-art performance in HPE-based applications. Although deep learning-based approaches have achieved remarkable performance in HPE, a comprehensive review of deep learning-based HPE methods remains lacking in the literature. In this article, we provide an up-to-date and in-depth overview of the deep learning approaches in vision-based HPE. We summarize these methods of 2-D and 3-D HPE, and their applications, discuss the challenges and the research trends through bibliometrics, and provide insightful recommendations for future research. This article provides a meaningful overview as introductory material for beginners to deep learning-based HPE, as well as supplementary material for advanced researchers.