To Örebro University

oru.seÖrebro University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Object-RPE: Dense 3D Reconstruction and Pose Estimation with Convolutional Neural Networks
Örebro University, School of Science and Technology. (Autonomous Mobile Manipulation Lab)
Örebro University, School of Science and Technology. (Centre for Applied Autonomous Sensor Systems (AASSS))ORCID iD: 0000-0003-0217-9326
Örebro University, School of Science and Technology. (Centre for Applied Autonomous Sensor Systems (AASS))ORCID iD: 0000-0002-6013-4874
2020 (English)In: Robotics and Autonomous Systems, ISSN 0921-8890, E-ISSN 1872-793X, Vol. 133, article id 103632Article in journal (Refereed) Published
Abstract [en]

We present an approach for recognizing objects present in a scene and estimating their full pose by means of an accurate 3D instance-aware semantic reconstruction. Our framework couples convolutional neural networks (CNNs) and a state-of-the-art dense Simultaneous Localisation and Mapping(SLAM) system, ElasticFusion [1], to achieve both high-quality semantic reconstruction as well as robust 6D pose estimation for relevant objects. We leverage the pipeline of ElasticFusion as a back-bone and propose a joint geometric and photometric error function with per-pixel adaptive weights. While the main trend in CNN-based 6D pose estimation has been to infer an object’s position and orientation from single views of the scene, our approach explores performing pose estimation from multiple viewpoints, under the conjecture that combining multiple predictions can improve the robustness of an object detection system. The resulting system is capable of producing high-quality instance-aware semantic reconstructions of room-sized environments, as well as accurately detecting objects and their 6D poses. The developed method has been verified through extensive experiments on different datasets. Experimental results confirmed that the proposed system achieves improvements over state-of-the-art methods in terms of surface reconstruction and object pose prediction. Our code and video are available at https://sites.google.com/view/object-rpe.

Place, publisher, year, edition, pages
Elsevier, 2020. Vol. 133, article id 103632
Keywords [en]
Object pose estimation, 3D reconstruction, Semantic mapping, 3D registration
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-88209DOI: 10.1016/j.robot.2020.103632ISI: 000558081900023Scopus ID: 2-s2.0-85090016097OAI: oai:DiVA.org:oru-88209DiVA, id: diva2:1513204
Funder
EU, Horizon 2020Available from: 2020-12-29 Created: 2020-12-29 Last updated: 2021-04-22Bibliographically approved

Open Access in DiVA

Object-RPE: Dense 3D reconstruction and pose estimation with convolutional neural networks(14196 kB)1284 downloads
File information
File name FULLTEXT01.pdfFile size 14196 kBChecksum SHA-512
8f9a8171d8ca47a472d1d43ff461235daf16f29d5ca42918accea7ae16907edd16f8d3b652d17bb151aed4a1aef35ed1e38b6ec3a3a4fa538f83d66c3316fe35
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Hoang, Dinh-CuongLilienthal, AchimStoyanov, Todor

Search in DiVA

By author/editor
Hoang, Dinh-CuongLilienthal, AchimStoyanov, Todor
By organisation
School of Science and Technology
In the same journal
Robotics and Autonomous Systems
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 1285 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 616 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf