Dot-coded structured light for accurate and robust 3D reconstruction
Authors:
- Feifei GuFGFeifei Gu
- Huazhao CaoHCHuazhao Cao
- Zhan SongZSZhan Song
- Pengju XiePXPengju Xie
- Juan ZhaoJZJuan Zhao
- Jing LiuJLJing Liu
- 20 November 2020
- journal article
- research article
- Published by Optica Publishing Group in Applied Optics
- Vol. 59 (33) , 10574-10583
Abstract
Speckle dots have the advantage of easy projection, which makes them good candidate features of structured light (SL) cameras, such as Kinect v1. However, they generally yield poor accuracy due to block matching. To improve their accuracy, this paper proposes a dot-coded SL, the coding information of which is added into dot distribution. Some of the dots are arranged regularly to provide easy-to-locate corner features, while others are specially designed to form different shapes of unique identification. A Gaussian-cross module and a simplified ResNet have been proposed to conduct robust decoding. Various experiments are performed to verify the accuracy and robustness of our framework.Keywords
Funding Information
- Key-Area Research and Development Program of Guangdong Province, China (2019B010149002)
- Natural Science Foundation of Guangdong Province (2020A1515010486, 2018A030310668)
- Natural Science Foundation of Shenzhen Municipality (JCYJ20190806171403585, JSGG20191129114035610)
- Dongguan City Core Technology Research Frontier Project (2019622101001)
This publication has 32 references indexed in Scilit:
- Real-time structured light profilometry: a reviewOptics and Lasers in Engineering, 2016
- Robot Guidance Using Machine Vision Techniques in Industrial Environments: A Comparative ReviewSensors, 2016
- Photometric invariant stereo matching methodOptics Express, 2015
- Kinect range sensing: Structured-light versus Time-of-Flight KinectComputer Vision and Image Understanding, 2015
- Real-time, high-accuracy 3D imaging and shape measurementApplied Optics, 2014
- Stereo Matching Using Tree FilteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Review of stereo vision algorithms and their suitability for resource-limited systemsJournal of Real-Time Image Processing, 2013
- A state of the art in structured light patterns for surface profilometryPattern Recognition, 2010
- Pattern codification strategies in structured light systemsPattern Recognition, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998