Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/82836
Title: 3D convolutional neural networks for efficient and robust hand pose estimation from single depth images
Authors: Ge, Liuhao
Liang, Hui
Yuan, Junsong
Thalmann, Daniel
Keywords: Three-dimensional Displays
Pose Estimation
Engineering::Electrical and electronic engineering
Issue Date: 2017
Source: Ge, L., Liang, H., Yuan, J., & Thalmann, D. (2017). 3D convolutional neural networks for efficient and robust hand pose estimation from single depth images. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/CVPR.2017.602
Abstract: We propose a simple, yet effective approach for real-time hand pose estimation from single depth images using three-dimensional Convolutional Neural Networks (3D CNNs). Image based features extracted by 2D CNNs are not directly suitable for 3D hand pose estimation due to the lack of 3D spatial information. Our proposed 3D CNN taking a 3D volumetric representation of the hand depth image as input can capture the 3D spatial structure of the input and accurately regress full 3D hand pose in a single pass. In order to make the 3D CNN robust to variations in hand sizes and global orientations, we perform 3D data augmentation on the training data. Experiments show that our proposed 3D CNN based approach outperforms state-of-the-art methods on two challenging hand pose datasets, and is very efficient as our implementation runs at over 215 fps on a standard computer with a single GPU.
URI: https://hdl.handle.net/10356/82836
http://hdl.handle.net/10220/50409
DOI: 10.1109/CVPR.2017.602
Rights: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/CVPR.2017.602
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IGS Conference Papers

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.