elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Applicability of Deep Learned vs Traditional Features for Depth Based Classification

Bracci, F and Li, M and Marton, Zoltan-Csaba and Kossyk, Ingo (2018) Applicability of Deep Learned vs Traditional Features for Depth Based Classification. In: 6th International Symposium on Computational Modeling of Objects Presented in Images, CompIMAGE 2018. Springer, Heidelberg. CompiImage18, Krakow, Poland. doi: 10.1007/978-3-030-20805-9_13. ISBN 978-3-030-20804-2.

[img] PDF
1MB

Official URL: https://www.springerprofessional.de/applicability-of-deep-learned-vs-traditional-features-for-depth-/16753580

Abstract

In robotic applications often highly specific objects need to be recognized, e.g. industrial parts, for which methods can’t rely on the online availability of large labeled training data sets or pre-trained mod- els. This is especially valid for depth data, thus making it challenging for deep learning (DL) approaches. Therefore, this work analyzes the per- formance of various traditional (global or part-based) and DL features on a restricted depth data set, depending on the tasks complexity. While the sample size is small, we can conclude that pre-trained DL descriptors are the most descriptive but not by a statistically significant margin and therefore part-based descriptors are still a viable option for small but difficult 3D data sets.

Item URL in elib:https://elib.dlr.de/124865/
Document Type:Conference or Workshop Item (Speech)
Title:Applicability of Deep Learned vs Traditional Features for Depth Based Classification
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Bracci, FUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Li, MUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Marton, Zoltan-CsabaUNSPECIFIEDhttps://orcid.org/0000-0002-3035-493XUNSPECIFIED
Kossyk, IngoUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:July 2018
Journal or Publication Title:6th International Symposium on Computational Modeling of Objects Presented in Images, CompIMAGE 2018
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
DOI:10.1007/978-3-030-20805-9_13
Editors:
EditorsEmailEditor's ORCID iDORCID Put Code
Barneva, RUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Publisher:Springer, Heidelberg
Series Name:Lecture Notes in Computer Science
ISBN:978-3-030-20804-2
Status:Published
Keywords:3D shape descriptor, point cloud descriptor, deep learning features, object recognition, scene analysis
Event Title:CompiImage18
Event Location:Krakow, Poland
Event Type:international Conference
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Terrestrial Assistance Robotics (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Bracci, Fabio
Deposited On:11 Dec 2018 23:00
Last Modified:11 Jul 2023 10:57

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.