A distributed source autoencoder of local visual descriptors for 3D reconstruction

•Application of a deep learning to the compression of local visual descriptors.•Combination of distributed source coding and autoencoders.•Definition of a low-complexity encoder suitable for mobile low-cost boards.•Competitive compression and reconstruction performances w.r.t existing solutions.•Opt...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pattern recognition letters Jg. 146; S. 193 - 199
1. Verfasser: Milani, Simone
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 01.06.2021
Elsevier Science Ltd
Schlagworte:
Autoencoder
Cameras
Coding
Computer applications
Distributed source coding
Distributed vision networks
Embedding
Local descriptor coding
Receivers-Decoders
Reconstruction
Structure-from-Motion
Distributed vision networks
Autoencoder
Local descriptor coding
Structure-from-Motion
Distributed source coding
ISSN:0167-8655, 1872-7344
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Application of a deep learning to the compression of local visual descriptors.•Combination of distributed source coding and autoencoders.•Definition of a low-complexity encoder suitable for mobile low-cost boards.•Competitive compression and reconstruction performances w.r.t existing solutions.•Optimization of the coding scheme for 3D scene reconstruction applications. [Display omitted] This paper presents a local descriptor coding scheme for multicamera surveillance and 3D reconstruction embedding an autoencoder into a traditional distributed source coding strategy. The proposed solution permits shifting most of the computational complexity at the decoder/receiver and exploiting the correlation among descriptors of different cameras (thus reducing the coded bit rate) without increasing the inter-device communication load. Experimental results show that the proposed scheme permits obtaining a satisfying accuracy with respect to the most recent solutions while generating a limited bit rate.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2021.03.019