A hand pose tracking benchmark from stereo matching

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

79 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages982-986
ISBN (electronic)978-1-5090-2175-8
Publication statusPublished - Sept 2017

Conference

Title24th IEEE International Conference on Image Processing (ICIP 2017)
LocationChina National Convention Center
PlaceChina
CityBeijing
Period17 - 20 September 2017

Abstract

In this paper we establish a long-term 3D hand pose tracking benchmark1. It contains 18,000 stereo image pairs as well as the ground-truth 3D positions of palm and finger joints from different scenarios. Meanwhile, to accurately segment hand from stereo images, we propose a novel stereo-based hand segmentation and depth estimation algorithm specially tailored for hand tracking here. The experiments indicate the effectiveness of the proposed algorithm by demonstrating that its tracking performance is comparable to the use of an active depth sensor under various of challenging scenarios.

Research Area(s)

  • Stereo matching and hand pose tracking

Citation Format(s)

A hand pose tracking benchmark from stereo matching. / Zhang, Jiawei; Jiao, Jianbo; Chen, Mingliang et al.
2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Institute of Electrical and Electronics Engineers, Inc., 2017. p. 982-986.

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review