Monocular human pose estimation: A survey of deep learning-based methods

2020/01/07 by Yucheng Chen, Yingli Tian, Mingyi He · 444 citations
Computer Science · Engineering · Mathematics · Medicine · #Artificial intelligence #Benchmark (surveying) #Computer science #Computer vision #Deep learning #Diabetic Foot Ulcer Assessment and Management #Engineering #Estimation #Field (mathematics) #Geography #Human Pose and Action Recognition #Machine learning #Mathematics #Monocular #Monocular vision #Pose #Video Surveillance and Tracking Methods #cs.CV

paper · pdf · doi:10.1016/j.cviu.2019.102897

published in Computer Vision and Image Understanding 192, 102897 (Elsevier BV) · This version corresponds to the pre-print of the paper accepted for Computer Vision and Image Understanding (CVIU)

openalex publication_date 2020/01/07 · arxiv created 2020/06/02 · arxiv updated 2020/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• SCAPE
• The Pascal Visual Object Classes (VOC) Challenge
• Generalized Procrustes Analysis
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• ImageNet classification with deep convolutional neural networks
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Numerical Coordinate Regression with Convolutional Neural Networks
• Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation
• Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn
• Multi-Person Pose Estimation with Local Joint-to-Person Associations
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• RMPE: Regional Multi-person Pose Estimation
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• Fully Convolutional Networks for Semantic Segmentation

Cited by

• Single Person Pose Estimation: A Survey
• Real-time human pose estimation on a smart walker using convolutional neural networks