UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Bi-Stream Pose-Guided Region Ensemble Network for Fingertip Localization From Stereo Images

Wang, G; Zhang, C; Chen, X; Ji, X; Xue, J-H; Wang, H; (2020) Bi-Stream Pose-Guided Region Ensemble Network for Fingertip Localization From Stereo Images. IEEE Transactions on Neural Networks and Learning Systems 10.1109/tnnls.2020.2964037. (In press). Green open access

[thumbnail of TNNLS-GuijinWang-CairongZhang-BiPoseREN-UCL.pdf]
Preview
Text
TNNLS-GuijinWang-CairongZhang-BiPoseREN-UCL.pdf - Accepted Version

Download (6MB) | Preview

Abstract

In human-computer interaction, it is important to accurately estimate the hand pose, especially fingertips. However, traditional approaches to fingertip localization mainly rely on depth images and thus suffer considerably from noise and missing values. Instead of depth images, stereo images can also provide 3-D information of hands. There are nevertheless limitations on the dataset size, global viewpoints, hand articulations, and hand shapes in publicly available stereo-based hand pose datasets. To mitigate these limitations and promote further research on hand pose estimation from stereo images, we build a new large-scale binocular hand pose dataset called THU-Bi-Hand, offering a new perspective for fingertip localization. In the THU-Bi-Hand dataset, there are 447k pairs of stereo images of different hand shapes from ten subjects with accurate 3-D location annotations of the wrist and five fingertips. Captured with minimal restriction on the range of hand motion, the dataset covers a large global viewpoint space and hand articulation space. To better present the performance of fingertip localization on THU-Bi-Hand, we propose a novel scheme termed bi-stream pose-guided region ensemble network (Bi-Pose-REN). It extracts more representative feature regions around joints in the feature maps under the guidance of the previously estimated pose. The feature regions are integrated hierarchically according to the topology of hand joints to regress a refined hand pose. Bi-Pose-REN and several existing methods are evaluated on THU-Bi-Hand so that benchmarks are provided for further research. Experimental results show that our Bi-Pose-REN has achieved the best performance on THU-Bi-Hand.

Type: Article
Title: Bi-Stream Pose-Guided Region Ensemble Network for Fingertip Localization From Stereo Images
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tnnls.2020.2964037
Publisher version: https://doi.org/10.1109/tnnls.2020.2964037
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Fingertip localization, Hand pose estimation, Region ensemble network, Human-computer interaction, Hand pose dataset.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10091122
Downloads since deposit
65Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item