onr:"swepub:oai:DiVA.org:oru-53369"
Search: onr:"swepub:oai:DiVA.org:oru-53369" > From Feature Detect...
- 1 of 1
- Previous record
- Next record
- To hitlist
From Feature Detection in Truncated Signed Distance Fields to Sparse Stable Scene Graphs
-
- Canelhas, Daniel R., 1983- (author)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems ( AASS )
-
- Stoyanov, Todor, 1984- (author)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems ( AASS )
-
- Lilienthal, Achim J., 1970- (author)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems ( AASS )
- (creator_code:org_t)
- Piscataway, USA : Institute of Electrical and Electronics Engineers (IEEE), 2016
- 2016
- English.
- In: IEEE Robotics and Automation Letters. - Piscataway, USA : Institute of Electrical and Electronics Engineers (IEEE). - 2377-3766. ; 1:2, s. 1148-1155
- Journal article (peer-reviewed)
Abstract
Subject headings
Close
- With the increased availability of GPUs and multicore CPUs, volumetric map representations are an increasingly viable option for robotic applications. A particularly important representation is the truncated signed distance field (TSDF) that is at the core of recent advances in dense 3D mapping. However, there is relatively little literature exploring the characteristics of 3D feature detection in volumetric representations. In this paper we evaluate the performance of features extracted directly from a 3D TSDF representation. We compare the repeatability of Integral invariant features, specifically designed for volumetric images, to the 3D extensions of Harris and Shi & Tomasi corners. We also study the impact of different methods for obtaining gradients for their computation. We motivate our study with an example application for building sparse stable scene graphs, and present an efficient GPU-parallel algorithm to obtain the graphs, made possible by the combination of TSDF and 3D feature points. Our findings show that while the 3D extensions of 2D corner-detection perform as expected, integral invariants have shortcomings when applied to discrete TSDFs. We conclude with a discussion of the cause for these points of failure that sheds light on possible mitigation strategies.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Keyword
- Mapping
- recognition
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
- IEEE Robotics and Automation Letters (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Canelhas, Daniel ...
- Stoyanov, Todor, ...
- Lilienthal, Achi ...
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Science ...
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Computer Vision ...
- Articles in the publication
- IEEE Robotics an ...
- By the university
- Örebro University
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
