Efficient Monocular Human Pose Estimation Based on Deep Learning Methods: A Survey

Xuke Yan

doi:10.1109/ACCESS.2024.3399222

Efficient Monocular Human Pose Estimation Based on Deep Learning Methods: A Survey

2024-01-01

3

OA

AI

DOI：10.1109/ACCESS.2024.3399222

原文链接

原文求助

摘要

En 中文

Human pose estimation (HPE) is a crucial computer vision task with a wide range of applications in sports medicine, healthcare, virtual reality, and human-computer interaction. The demand for real-time HPE solutions necessitates the development of efficient deep-learning models that can be deployed on resource-constrained devices. While a few surveys exist in this area, none delve deeply into the critical intersection of efficiency and performance. This survey reviews the state-of-the-art efficient deep learning approaches for real-time HPE, focusing on strategies for improving efficiency without compromising accuracy. We discuss popular backbone networks for HPE, model compression techniques, network pruning and quantization, knowledge distillation, and neural architecture search methods. Furthermore, we critically analyze the existing works, highlighting their strengths, weaknesses, and applicability to different scenarios. We also present an overview of the evaluation datasets, metrics, and design for efficient HPE. Finally, we identify research gaps and challenges in the field, providing insights and recommendations for future research directions in developing efficient and scalable HPE solutions.

Keyword:

Three-dimensional displays

Pose estimation

Surveys

Real-time systems

Deep learning

Solid modeling

Computational modeling

Survey

2D human pose estimation

3D human pose estimation

deep learning

efficiency

Efficient Monocular Human Pose Estimation Based on Deep Learning Methods: A Survey

摘要

期刊

机构