3D object discovery and modeling using single RGB-D images containing multiple object instancesShow others and affiliations
2018 (English)In: Proceedings - 2017 International Conference on 3D Vision, 3DV 2017, Institute of Electrical and Electronics Engineers (IEEE), 2018, p. 431-439Conference paper, Published paper (Refereed)
Abstract [en]
Unsupervised object modeling is important in robotics, especially for handling a large set of objects. We present a method for unsupervised 3D object discovery, reconstruction, and localization that exploits multiple instances of an identical object contained in a single RGB-D image. The proposed method does not rely on segmentation, scene knowledge, or user input, and thus is easily scalable. Our method aims to find recurrent patterns in a single RGB-D image by utilizing appearance and geometry of the salient regions. We extract keypoints and match them in pairs based on their descriptors. We then generate triplets of the keypoints matching with each other using several geometric criteria to minimize false matches. The relative poses of the matched triplets are computed and clustered to discover sets of triplet pairs with similar relative poses. Triplets belonging to the same set are likely to belong to the same object and are used to construct an initial object model. Detection of remaining instances with the initial object model using RANSAC allows to further expand and refine the model. The automatically generated object models are both compact and descriptive. We show quantitative and qualitative results on RGB-D images with various objects including some from the Amazon Picking Challenge. We also demonstrate the use of our method in an object picking scenario with a robotic arm.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2018. p. 431-439
Keywords [en]
Computer-vision, Discovery, Keypoints, Matching, Pose-estimation, Reconstruction, RGB-D, Robotics, Unsupervised
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:kth:diva-238227DOI: 10.1109/3DV.2017.00056ISI: 000454981700046Scopus ID: 2-s2.0-85048838691ISBN: 9781538626108 (print)OAI: oai:DiVA.org:kth-238227DiVA, id: diva2:1263045
Conference
7th IEEE International Conference on 3D Vision, 3DV 2017, Qingdao, China, 10 October 2017 through 12 October 2017
Note
QC 20181114
2018-11-142018-11-142022-06-26Bibliographically approved