Point Set Registration With Semantic Region Association Using Cascaded Expectation Maximization
Lan Hu; Jiaxin Wei; Laurent Kneip
2021
Source PublicationIEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION
Status正式接收
DOI-
Abstract

We introduce a new solution to point set registration, a fundamental geometric problem occurring in many computer vision and robotics applications. We consider the specific case in which the point sets are segmented into semantically annotated parts. Such information may for example come from object detection or instance-level semantic segmentation in a registered RGB image. Existing methods incorporate the additional information to restrict or re-weight the point-pair associations occurring throughout the registration process. We introduce a novel hierarchical association framework for a simultaneous inference of semantic region association likelihoods. The formulation is elegantly solved using cascaded expectationmaximization. We conclude by demonstrating a substantial improvement over existing alternatives on open RGBD datasets.

Author of SourceICRA
Language英语
Document Type会议论文
Identifierhttps://kms.shanghaitech.edu.cn/handle/2MSLDSTB/126752
Collection信息科学与技术学院_PI研究组_Laurent Kneip组
信息科学与技术学院_博士生
AffiliationShanghaiTech University
Recommended Citation
GB/T 7714
Lan Hu,Jiaxin Wei,Laurent Kneip. Point Set Registration With Semantic Region Association Using Cascaded Expectation Maximization[C]//ICRA,2021.
Files in This Item:
File Name/Size DocType Version Access License
icra_2021_hulan_weij(2511KB)会议论文 限制开放CC BY-NC-SAView Application Full Text
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Lan Hu]'s Articles
[Jiaxin Wei]'s Articles
[Laurent Kneip]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lan Hu]'s Articles
[Jiaxin Wei]'s Articles
[Laurent Kneip]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lan Hu]'s Articles
[Jiaxin Wei]'s Articles
[Laurent Kneip]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: icra_2021_hulan_weijiaxin.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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