Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices

Sheng Chu Huang; Wei Lun Huang; Yi Cheng Lu; Ming Han Tsai; I-Chen Lin; Yo Chung Lau; Hsu Hang Liu

doi:10.5220/0007692603750382

Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices

Sheng Chu Huang, Wei Lun Huang, Yi Cheng Lu, Ming Han Tsai, I-Chen Lin, Yo Chung Lau, Hsu Hang Liu

多媒體工程研究所

研究成果: Paper › 同行評審

1 引文斯高帕斯（Scopus）

摘要

This paper presents a system that can efficiently detect objects and estimate their 6D postures with RGB-D and motion sensor data on a mobile device. We apply a template-based method to detect the pose of an object, in which the matching process is accelerated through dimension reduction of the vectorized template matrix. After getting the initial pose, the proposed system then tracks the detected objects by a modified bidirectional iterative closest point algorithm. Furthermore, our system checks information from the inertial measurement unit on a mobile device to alleviate intensive computation for ease of interactive applications.

原文	American English
頁面	375-382
頁數	8
DOIs	https://doi.org/10.5220/0007692603750382
出版狀態	Published - 25 2月 2019
事件	14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 - Prague, Czech Republic 持續時間: 25 2月 2019 → 27 2月 2019

Conference

Conference	14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019
國家/地區	Czech Republic
城市	Prague
期間	25/02/19 → 27/02/19

存取文件

10.5220/0007692603750382

其它文件與鏈接

Link to publication in Scopus

引用此

Huang, S. C., Huang, W. L., Lu, Y. C., Tsai, M. H., Lin, I-C., Lau, Y. C., & Liu, H. H. (2019). Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices. 375-382. 論文發表於 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic. https://doi.org/10.5220/0007692603750382

Huang, Sheng Chu ; Huang, Wei Lun ; Lu, Yi Cheng 等. / Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices. 論文發表於 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic.8 p.

@conference{17490432a1c0491f9b3e3b2928e11e37,

title = "Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices",

abstract = "This paper presents a system that can efficiently detect objects and estimate their 6D postures with RGB-D and motion sensor data on a mobile device. We apply a template-based method to detect the pose of an object, in which the matching process is accelerated through dimension reduction of the vectorized template matrix. After getting the initial pose, the proposed system then tracks the detected objects by a modified bidirectional iterative closest point algorithm. Furthermore, our system checks information from the inertial measurement unit on a mobile device to alleviate intensive computation for ease of interactive applications.",

keywords = "Markerless Tracking, Object Recognition, Pose Estimation, Sensors on Mobile Devices",

author = "Huang, {Sheng Chu} and Huang, {Wei Lun} and Lu, {Yi Cheng} and Tsai, {Ming Han} and I-Chen Lin and Lau, {Yo Chung} and Liu, {Hsu Hang}",

year = "2019",

month = feb,

day = "25",

doi = "10.5220/0007692603750382",

language = "American English",

pages = "375--382",

note = "14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 ; Conference date: 25-02-2019 Through 27-02-2019",

}

Huang, SC, Huang, WL, Lu, YC, Tsai, MH, Lin, I-C, Lau, YC & Liu, HH 2019, 'Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices', 論文發表於 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic, 25/02/19 - 27/02/19 頁 375-382. https://doi.org/10.5220/0007692603750382

Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices. / Huang, Sheng Chu; Huang, Wei Lun; Lu, Yi Cheng 等.

2019. 375-382 論文發表於 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic.

研究成果: Paper › 同行評審

TY - CONF

T1 - Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices

AU - Huang, Sheng Chu

AU - Huang, Wei Lun

AU - Lu, Yi Cheng

AU - Tsai, Ming Han

AU - Lin, I-Chen

AU - Lau, Yo Chung

AU - Liu, Hsu Hang

PY - 2019/2/25

Y1 - 2019/2/25

N2 - This paper presents a system that can efficiently detect objects and estimate their 6D postures with RGB-D and motion sensor data on a mobile device. We apply a template-based method to detect the pose of an object, in which the matching process is accelerated through dimension reduction of the vectorized template matrix. After getting the initial pose, the proposed system then tracks the detected objects by a modified bidirectional iterative closest point algorithm. Furthermore, our system checks information from the inertial measurement unit on a mobile device to alleviate intensive computation for ease of interactive applications.

AB - This paper presents a system that can efficiently detect objects and estimate their 6D postures with RGB-D and motion sensor data on a mobile device. We apply a template-based method to detect the pose of an object, in which the matching process is accelerated through dimension reduction of the vectorized template matrix. After getting the initial pose, the proposed system then tracks the detected objects by a modified bidirectional iterative closest point algorithm. Furthermore, our system checks information from the inertial measurement unit on a mobile device to alleviate intensive computation for ease of interactive applications.

KW - Markerless Tracking

KW - Object Recognition

KW - Pose Estimation

KW - Sensors on Mobile Devices

UR - http://www.scopus.com/inward/record.url?scp=85068233455&partnerID=8YFLogxK

U2 - 10.5220/0007692603750382

DO - 10.5220/0007692603750382

M3 - Paper

AN - SCOPUS:85068233455

SP - 375

EP - 382

T2 - 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019

Y2 - 25 February 2019 through 27 February 2019

ER -

Huang SC, Huang WL, Lu YC, Tsai MH, Lin I-C, Lau YC 等. Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices. 2019. 論文發表於 14th International Conference on Computer Graphics Theory and Applications, GRAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic. doi: 10.5220/0007692603750382

Efficient recognition and 6D pose tracking of markerless objects with RGB-D and motion sensors on mobile devices

摘要

Conference

存取文件

其它文件與鏈接

指紋

引用此