Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods

TL;DR

This survey reviews recent deep learning methods for monocular 2D and 3D human pose estimation, highlighting progress, challenges, datasets, and future directions in the field.

Contribution

It provides a comprehensive overview of deep learning-based human pose estimation techniques, summarizing developments since 2014 and discussing future research opportunities.

Findings

Deep learning has significantly advanced pose estimation accuracy.

Benchmark datasets and evaluation metrics are crucial for progress.

Future research directions include addressing challenges like occlusion and real-time processing.

Abstract

Vision-based monocular human pose estimation, as one of the most fundamental and challenging problems in computer vision, aims to obtain posture of the human body from input images or video sequences. The recent developments of deep learning techniques have been brought significant progress and remarkable breakthroughs in the field of human pose estimation. This survey extensively reviews the recent deep learning-based 2D and 3D human pose estimation methods published since 2014. This paper summarizes the challenges, main frameworks, benchmark datasets, evaluation metrics, performance comparison, and discusses some promising future research directions.