Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Structure aware SLAM using quadrics and planes
Author: Hosseinzadeh, M.
Latif, Y.
Pham, T.
Suenderhauf, N.
Reid, I.
Citation: Proceedings of the 14th Asian Conference on Computer Vision (ACCV 2018), as published in Lecture Notes in Computer Science, 2019 / vol.11363, pp.410-426
Publisher: Springer
Publisher Place: Switzerlaned
Issue Date: 2019
Series/Report no.: Lecture Notes in Computer Science ; 11363
ISBN: 9783030208929
ISSN: 0302-9743
Conference Name: Asian Conference on Computer Vision (ACCV) (02 Dec 2018 - 06 Dec 2018 : Perth, Australia)
Statement of
Mehdi Hosseinzadeh, Yasir Latif, Trung Pham, Niko Suenderhauf, and Ian Reid
Abstract: Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work marries the two and proposes a method for representing generic objects as quadrics which allows object detections to be seamlessly integrated in a SLAM framework. For scene coverage, additional dominant planar structures are modeled as infinite planes. Experiments show that the proposed points-planes-quadrics representation can easily incorporate Manhattan and object affordance constraints, greatly improving camera localization and leading to semantically meaningful maps.
Keywords: Visual semantic SLAM; Object SLAM; Planes; Quadrics
Rights: © Springer Nature Switzerland AG 2019
RMID: 0030118533
DOI: 10.1007/978-3-030-20893-6_26
Grant ID:
Published version:
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.

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