CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Robust and Efficient CPU-based RGB-D Scene Reconstruction
Li JW(李建伟)1,2; Gao W(高伟)1,2; Li HP(李和平)1,2; Tang FL(唐付林)1,2; Wu YH(吴毅红)1,2
Source PublicationSensors
2018
Volume18Issue:11Pages:3652-3667
Abstract
3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along camera trajectory, each view containing a small part of the scene. Tracking in textureless scenes is well known to be a Gordian knot of camera tracking, and how to obtain accurate 3D models quickly is a major challenge for existing systems. For the application of robotics, we propose a robust CPU-based approach to efficiently reconstruct indoor scene with a consumer RGB-D camera. The proposed approach bridges feature-based camera tracking and volumetric-based data integration together, and has a good reconstruction performance in terms of both robustness and efficiency. The key points in our approach include: 1) a robust and fast camera tracking method combining points and edges, which improves tracking stability in textureless scenes; 2) an efficient data fusion strategy to select camera views and integrate RGB-D images on multiple scales, which enhances the efficiency of volumetric integration; 3) a novel RGB-D scene reconstruction system, which can be quickly implemented on a standard CPU. Experimental results demonstrate that our approach reconstructs scenes with higher robustness and efficiency compared to state-of-the-art reconstruction systems.
Keyword3d Reconstruction Camera Tracking Volumetric Integration Simultaneous Localization And Mapping (Slam)}
Indexed BySCIE
Language英语
WOS IDWOS:000451598900062
Citation statistics
Cited Times:3[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23360
Collection模式识别国家重点实验室_机器人视觉
机器人视觉团队
Corresponding AuthorGao W(高伟)
Affiliation1.中科院自动化研究所
2.中国科学院大学
Recommended Citation
GB/T 7714
Li JW,Gao W,Li HP,et al. Robust and Efficient CPU-based RGB-D Scene Reconstruction[J]. Sensors,2018,18(11):3652-3667.
APA Li JW,Gao W,Li HP,Tang FL,&Wu YH.(2018).Robust and Efficient CPU-based RGB-D Scene Reconstruction.Sensors,18(11),3652-3667.
MLA Li JW,et al."Robust and Efficient CPU-based RGB-D Scene Reconstruction".Sensors 18.11(2018):3652-3667.
Files in This Item: Download All
File Name/Size DocType Version Access License
sensors-18-03652-v2.(4363KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li JW(李建伟)]'s Articles
[Gao W(高伟)]'s Articles
[Li HP(李和平)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li JW(李建伟)]'s Articles
[Gao W(高伟)]'s Articles
[Li HP(李和平)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li JW(李建伟)]'s Articles
[Gao W(高伟)]'s Articles
[Li HP(李和平)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: sensors-18-03652-v2.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.