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

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.

This version corresponds to the pre-print of the paper accepted for Computer Vision and Image Understanding (CVIU)

References in corpus (21)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Fully Convolutional Networks for Semantic Segmentation
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Learning from Synthetic Humans
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Human pose estimation via Convolutional Part Heatmap Regression
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• Learning Human Pose Estimation Features with Convolutional Networks
• Numerical Coordinate Regression with Convolutional Neural Networks
• AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
• R-CNNs for Pose Estimation and Action Detection
• 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
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Multi-Person Pose Estimation with Local Joint-to-Person Associations
• DRPose3D: Depth Ranking in 3D Human Pose Estimation
• Skeleton Boxes: Solving skeleton based action detection with a single deep convolutional neural network

Cited by in corpus (26)

• Recovering 3D Human Mesh from Monocular Images: A Survey
• MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
• Vision-Based Human Pose Estimation via Deep Learning: A Survey
• Deep Learning-Based Human Pose Estimation: A Survey
• Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models
• Deep Learning based Virtual Point Tracking for Real-Time Target-less Dynamic Displacement Measurement in Railway Applications
• Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networks
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• Markerless Multi-view 3D Human Pose Estimation: a survey
• Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment
• Unveiling the frontiers of deep learning: innovations shaping diverse domains
• Privacy-Preserving In-Bed Pose Monitoring: A Fusion and Reconstruction Study
• S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
• Anatomy-guided domain adaptation for 3D in-bed human pose estimation
• Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements
• End-to-End Trainable Multi-Instance Pose Estimation with Transformers
• Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
• User-oriented Natural Human-Robot Control with Thin-Plate Splines and LRCN
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• A Survey on Human Interaction Motion Generation
• Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?
• Single Person Pose Estimation: A Survey
• WildGait: Learning Gait Representations from Raw Surveillance Streams
• Real-Time Human Fall Detection using a Lightweight Pose Estimation Technique
• Skeleton-based Approaches based on Machine Vision: A Survey
• Real-time RGBD-based Extended Body Pose Estimation