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

2019

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.

Download


Paper Citation


in Harvard Style

Huang S., Huang W., Lu Y., Tsai M., Lin I., Lau Y. and Liu H. (2019). Efficient Recognition and 6D Pose Tracking of Markerless Objects with RGB-D and Motion Sensors on Mobile Devices. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP; ISBN 978-989-758-354-4, SciTePress, pages 375-382. DOI: 10.5220/0007692603750382


in Bibtex Style

@conference{grapp19,
author={Sheng-Chu Huang and Wei-Lun Huang and Yi-Cheng Lu and Ming-Han Tsai and I-Chen Lin and Yo-Chung Lau and Hsu-Hang Liu},
title={Efficient Recognition and 6D Pose Tracking of Markerless Objects with RGB-D and Motion Sensors on Mobile Devices},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP},
year={2019},
pages={375-382},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007692603750382},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 1: GRAPP
TI - Efficient Recognition and 6D Pose Tracking of Markerless Objects with RGB-D and Motion Sensors on Mobile Devices
SN - 978-989-758-354-4
AU - Huang S.
AU - Huang W.
AU - Lu Y.
AU - Tsai M.
AU - Lin I.
AU - Lau Y.
AU - Liu H.
PY - 2019
SP - 375
EP - 382
DO - 10.5220/0007692603750382
PB - SciTePress