Sökning: id:"swepub:oai:DiVA.org:oru-64420" >
Compressed Voxel-Ba...
Compressed Voxel-Based Mapping Using Unsupervised Learning
-
- Canelhas, Daniel R., 1983- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Center for Autonomous Applied Sensor Systems (AASS)
-
- Schaffernicht, Erik, 1980- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Center for Autonomous Applied Sensor Systems (AASS)
-
- Stoyanov, Todor, 1984- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Center for Autonomous Applied Sensor Systems (AASS)
-
visa fler...
-
- Lilienthal, Achim, 1970- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Center for Autonomous Applied Sensor Systems (AASS)
-
- Davison, Andrew J. (författare)
- Department of Computing, Imperial College London, London, United Kingdom
-
visa färre...
-
(creator_code:org_t)
- 2017-06-29
- 2017
- Engelska.
-
Ingår i: Robotics. - Basel, Switzerland : MDPI AG. - 2218-6581. ; 6:3
- Relaterad länk:
-
https://doi.org/10.3...
-
visa fler...
-
https://www.mdpi.com...
-
https://urn.kb.se/re...
-
https://doi.org/10.3...
-
visa färre...
Abstract
Ämnesord
Stäng
- In order to deal with the scaling problem of volumetric map representations, we propose spatially local methods for high-ratio compression of 3D maps, represented as truncated signed distance fields. We show that these compressed maps can be used as meaningful descriptors for selective decompression in scenarios relevant to robotic applications. As compression methods, we compare using PCA-derived low-dimensional bases to nonlinear auto-encoder networks. Selecting two application-oriented performance metrics, we evaluate the impact of different compression rates on reconstruction fidelity as well as to the task of map-aided ego-motion estimation. It is demonstrated that lossily reconstructed distance fields used as cost functions for ego-motion estimation can outperform the original maps in challenging scenarios from standard RGB-D (color plus depth) data sets due to the rejection of high-frequency noise content.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- 3D mapping
- TSDF
- compression
- dictionary learning
- auto-encoder
- denoising
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
-
Robotics
(Sök värdpublikationen i LIBRIS)
Till lärosätets databas