Bracci, F und Li, M und Marton, Zoltan-Csaba und 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, 2018-07-02 - 2018-07-05, Krakow, Poland. doi: 10.1007/978-3-030-20805-9_13. ISBN 978-3-030-20804-2.
PDF
1MB |
Offizielle URL: https://www.springerprofessional.de/applicability-of-deep-learned-vs-traditional-features-for-depth-/16753580
Kurzfassung
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.
elib-URL des Eintrags: | https://elib.dlr.de/124865/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||||||||||
Titel: | Applicability of Deep Learned vs Traditional Features for Depth Based Classification | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | Juli 2018 | ||||||||||||||||||||
Erschienen in: | 6th International Symposium on Computational Modeling of Objects Presented in Images, CompIMAGE 2018 | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||||||
DOI: | 10.1007/978-3-030-20805-9_13 | ||||||||||||||||||||
Herausgeber: |
| ||||||||||||||||||||
Verlag: | Springer, Heidelberg | ||||||||||||||||||||
Name der Reihe: | Lecture Notes in Computer Science | ||||||||||||||||||||
ISBN: | 978-3-030-20804-2 | ||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||
Stichwörter: | 3D shape descriptor, point cloud descriptor, deep learning features, object recognition, scene analysis | ||||||||||||||||||||
Veranstaltungstitel: | CompiImage18 | ||||||||||||||||||||
Veranstaltungsort: | Krakow, Poland | ||||||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||||||
Veranstaltungsbeginn: | 2 Juli 2018 | ||||||||||||||||||||
Veranstaltungsende: | 5 Juli 2018 | ||||||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||||||||||
HGF - Programmthema: | Technik für Raumfahrtsysteme | ||||||||||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||||||
DLR - Forschungsgebiet: | R SY - Technik für Raumfahrtsysteme | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Terrestrische Assistenz-Robotik (alt) | ||||||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) | ||||||||||||||||||||
Hinterlegt von: | Bracci, Fabio | ||||||||||||||||||||
Hinterlegt am: | 11 Dez 2018 23:00 | ||||||||||||||||||||
Letzte Änderung: | 04 Jun 2024 12:45 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags