Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments
Three-dimensional hand detection from a single RGB-D image is an important technology which supports many useful applications. Practically, it is challenging to robustly detect human hands in unconstrained environments because the RGB-D channels can be affected by many uncontrollable factors, such a...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/21/6360 |
_version_ | 1797548564082065408 |
---|---|
author | Chi Xu Jun Zhou Wendi Cai Yunkai Jiang Yongbo Li Yi Liu |
author_facet | Chi Xu Jun Zhou Wendi Cai Yunkai Jiang Yongbo Li Yi Liu |
author_sort | Chi Xu |
collection | DOAJ |
description | Three-dimensional hand detection from a single RGB-D image is an important technology which supports many useful applications. Practically, it is challenging to robustly detect human hands in unconstrained environments because the RGB-D channels can be affected by many uncontrollable factors, such as light changes. To tackle this problem, we propose a 3D hand detection approach which improves the robustness and accuracy by adaptively fusing the complementary features extracted from the RGB-D channels. Using the fused RGB-D feature, the 2D bounding boxes of hands are detected first, and then the 3D locations along the z-axis are estimated through a cascaded network. Furthermore, we represent a challenging RGB-D hand detection dataset collected in unconstrained environments. Different from previous works which primarily rely on either the RGB or D channel, we adaptively fuse the RGB-D channels for hand detection. Specifically, evaluation results show that the D-channel is crucial for hand detection in unconstrained environments. Our RGB-D fusion-based approach significantly improves the hand detection accuracy from 69.1 to 74.1 comparing to one of the most state-of-the-art RGB-based hand detectors. The existing RGB- or D-based methods are unstable in unseen lighting conditions: in dark conditions, the accuracy of the RGB-based method significantly drops to 48.9, and in back-light conditions, the accuracy of the D-based method dramatically drops to 28.3. Compared with these methods, our RGB-D fusion based approach is much more robust without accuracy degrading, and our detection results are 62.5 and 65.9, respectively, in these two extreme lighting conditions for accuracy. |
first_indexed | 2024-03-10T15:01:19Z |
format | Article |
id | doaj.art-aa6fe93573f344ababa13ac43725068c |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T15:01:19Z |
publishDate | 2020-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-aa6fe93573f344ababa13ac43725068c2023-11-20T20:08:57ZengMDPI AGSensors1424-82202020-11-012021636010.3390/s20216360Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained EnvironmentsChi Xu0Jun Zhou1Wendi Cai2Yunkai Jiang3Yongbo Li4Yi Liu5School of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaCRRC Zhuzhou Electric Locomotive Co., Ltd., Zhuzhou 412000, ChinaThree-dimensional hand detection from a single RGB-D image is an important technology which supports many useful applications. Practically, it is challenging to robustly detect human hands in unconstrained environments because the RGB-D channels can be affected by many uncontrollable factors, such as light changes. To tackle this problem, we propose a 3D hand detection approach which improves the robustness and accuracy by adaptively fusing the complementary features extracted from the RGB-D channels. Using the fused RGB-D feature, the 2D bounding boxes of hands are detected first, and then the 3D locations along the z-axis are estimated through a cascaded network. Furthermore, we represent a challenging RGB-D hand detection dataset collected in unconstrained environments. Different from previous works which primarily rely on either the RGB or D channel, we adaptively fuse the RGB-D channels for hand detection. Specifically, evaluation results show that the D-channel is crucial for hand detection in unconstrained environments. Our RGB-D fusion-based approach significantly improves the hand detection accuracy from 69.1 to 74.1 comparing to one of the most state-of-the-art RGB-based hand detectors. The existing RGB- or D-based methods are unstable in unseen lighting conditions: in dark conditions, the accuracy of the RGB-based method significantly drops to 48.9, and in back-light conditions, the accuracy of the D-based method dramatically drops to 28.3. Compared with these methods, our RGB-D fusion based approach is much more robust without accuracy degrading, and our detection results are 62.5 and 65.9, respectively, in these two extreme lighting conditions for accuracy.https://www.mdpi.com/1424-8220/20/21/63603D hand detectionRGB-D sensorhuman–computer interactionunseen lighting conditionadaptive RGB-D fusion |
spellingShingle | Chi Xu Jun Zhou Wendi Cai Yunkai Jiang Yongbo Li Yi Liu Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments Sensors 3D hand detection RGB-D sensor human–computer interaction unseen lighting condition adaptive RGB-D fusion |
title | Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments |
title_full | Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments |
title_fullStr | Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments |
title_full_unstemmed | Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments |
title_short | Robust 3D Hand Detection from a Single RGB-D Image in Unconstrained Environments |
title_sort | robust 3d hand detection from a single rgb d image in unconstrained environments |
topic | 3D hand detection RGB-D sensor human–computer interaction unseen lighting condition adaptive RGB-D fusion |
url | https://www.mdpi.com/1424-8220/20/21/6360 |
work_keys_str_mv | AT chixu robust3dhanddetectionfromasinglergbdimageinunconstrainedenvironments AT junzhou robust3dhanddetectionfromasinglergbdimageinunconstrainedenvironments AT wendicai robust3dhanddetectionfromasinglergbdimageinunconstrainedenvironments AT yunkaijiang robust3dhanddetectionfromasinglergbdimageinunconstrainedenvironments AT yongboli robust3dhanddetectionfromasinglergbdimageinunconstrainedenvironments AT yiliu robust3dhanddetectionfromasinglergbdimageinunconstrainedenvironments |