Using a Single RGB Frame for Real Time 3D Hand Pose Estimation in the Wild
Authors:
- Paschalis PantelerisPPPaschalis Panteleris
- Iason OikonomidisIOIason Oikonomidis
- Antonis ArgyrosAAAntonis Argyros
- 1 March 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 436-445
Abstract
We present a method for the real-time estimation of the full 3D pose of one or more human hands using a single commodity RGB camera. Recent work in the area has displayed impressive progress using RGBD input. However, since the introduction of RGBD sensors, there has been little progress for the case of monocular color input. We capitalize on the latest advancements of deep learning, combining them with the power of generative hand pose estimation techniques to achieve real-time monocular 3D hand pose estimation in unrestricted scenarios. More specifically, given an RGB image and the relevant camera calibration information, we employ a state-of-the-art detector to localize hands. Given a crop of a hand in the image, we run the pretrained network of OpenPose for hands to estimate the 2D location of hand joints. Finally, non-linear least-squares minimization fits a 3D model of the hand to the estimated 2D joint positions, recovering the 3D hand pose. Extensive experimental results provide comparison to the state of the art as well as qualitative assessment of the method in the wild.Keywords
All Related Versions
This publication has 59 references indexed in Scilit:
- Back to RGB: 3D Tracking of Hands and Hand-Object Interactions Based on Short-Baseline Stereo2017
- Learning to Estimate 3D Hand Pose from Single RGB Images2017
- YOLO9000: Better, Faster, Stronger2017
- Efficiently Creating 3D Training Data for Fine Hand Pose Estimation2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Training a Feedback Loop for Hand Pose Estimation2015
- Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties2015
- Realtime and Robust Hand Tracking from Depth2014
- Efficient Hand Pose Estimation from a Single Depth Image2013
- Efficient model-based 3D tracking of hand articulations using Kinect2011