An adaptive local binary pattern for 3D hand tracking

Joongrock Kim, Sunjin Yu, Dongchul Kim, Kar Ann Toh, Sang Youn Lee

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Ever since the availability of real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor, the performance of gesture recognition can be largely enhanced. However, since conventional two-dimensional (2D) image based feature extraction methods such as local binary pattern (LBP) generally use texture information, they cannot be applied to depth or range image which does not contain texture information. In this paper, we propose an adaptive local binary pattern (ALBP) for effective depth images based applications. Contrasting to the conventional LBP which is only rotation invariant, the proposed ALBP is invariant to both rotation and the depth distance in range images. Using ALBP, we can extract object features without using texture or color information. We further apply the proposed ALBP for hand tracking using depth images to show its effectiveness and its usefulness. Our experimental results validate the proposal.

Original languageEnglish
Pages (from-to)139-152
Number of pages14
JournalPattern Recognition
Volume61
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Textures
Gesture recognition
Sensors
Feature extraction
Data acquisition
Availability
Color

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Kim, Joongrock ; Yu, Sunjin ; Kim, Dongchul ; Toh, Kar Ann ; Lee, Sang Youn. / An adaptive local binary pattern for 3D hand tracking. In: Pattern Recognition. 2017 ; Vol. 61. pp. 139-152.
@article{e2693832649a4f0d85dacb135f3155ec,
title = "An adaptive local binary pattern for 3D hand tracking",
abstract = "Ever since the availability of real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor, the performance of gesture recognition can be largely enhanced. However, since conventional two-dimensional (2D) image based feature extraction methods such as local binary pattern (LBP) generally use texture information, they cannot be applied to depth or range image which does not contain texture information. In this paper, we propose an adaptive local binary pattern (ALBP) for effective depth images based applications. Contrasting to the conventional LBP which is only rotation invariant, the proposed ALBP is invariant to both rotation and the depth distance in range images. Using ALBP, we can extract object features without using texture or color information. We further apply the proposed ALBP for hand tracking using depth images to show its effectiveness and its usefulness. Our experimental results validate the proposal.",
author = "Joongrock Kim and Sunjin Yu and Dongchul Kim and Toh, {Kar Ann} and Lee, {Sang Youn}",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.patcog.2016.07.039",
language = "English",
volume = "61",
pages = "139--152",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

An adaptive local binary pattern for 3D hand tracking. / Kim, Joongrock; Yu, Sunjin; Kim, Dongchul; Toh, Kar Ann; Lee, Sang Youn.

In: Pattern Recognition, Vol. 61, 01.01.2017, p. 139-152.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An adaptive local binary pattern for 3D hand tracking

AU - Kim, Joongrock

AU - Yu, Sunjin

AU - Kim, Dongchul

AU - Toh, Kar Ann

AU - Lee, Sang Youn

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Ever since the availability of real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor, the performance of gesture recognition can be largely enhanced. However, since conventional two-dimensional (2D) image based feature extraction methods such as local binary pattern (LBP) generally use texture information, they cannot be applied to depth or range image which does not contain texture information. In this paper, we propose an adaptive local binary pattern (ALBP) for effective depth images based applications. Contrasting to the conventional LBP which is only rotation invariant, the proposed ALBP is invariant to both rotation and the depth distance in range images. Using ALBP, we can extract object features without using texture or color information. We further apply the proposed ALBP for hand tracking using depth images to show its effectiveness and its usefulness. Our experimental results validate the proposal.

AB - Ever since the availability of real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor, the performance of gesture recognition can be largely enhanced. However, since conventional two-dimensional (2D) image based feature extraction methods such as local binary pattern (LBP) generally use texture information, they cannot be applied to depth or range image which does not contain texture information. In this paper, we propose an adaptive local binary pattern (ALBP) for effective depth images based applications. Contrasting to the conventional LBP which is only rotation invariant, the proposed ALBP is invariant to both rotation and the depth distance in range images. Using ALBP, we can extract object features without using texture or color information. We further apply the proposed ALBP for hand tracking using depth images to show its effectiveness and its usefulness. Our experimental results validate the proposal.

UR - http://www.scopus.com/inward/record.url?scp=84988632661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988632661&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2016.07.039

DO - 10.1016/j.patcog.2016.07.039

M3 - Article

VL - 61

SP - 139

EP - 152

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -