Logo des Repositoriums
 

Evaluation of CNN architectures for gait recognition based on optical flow maps

Kurzanzeige
dc.contributor.authorCastro,Francisco M.
dc.contributor.authorMarín-Jiménez,Manuel J.
dc.contributor.authorGuil,Nicolás
dc.contributor.authorLópez-Tapia,Santiago
dc.contributor.authorde la Blanca,Nicolás Pérez
dc.contributor.editorBrömme,Arslan
dc.contributor.editorBusch,Christoph
dc.contributor.editorDantcheva,Antitza
dc.contributor.editorRathgeb,Christian
dc.contributor.editorUhl,Andreas
dc.date.accessioned2017-09-26T09:21:01Z
dc.date.available2017-09-26T09:21:01Z
dc.date.issued2017
dc.description.abstractThis work targets people identification in video based on the way they walk (i.e.gait) by using deep learning architectures. We explore the use of convolutional neural networks (CNN) for learning high-level descriptors from low-level motion features (i.e.optical flow components). The low number of training samples for each subject and the use of a test set containing subjects different from the training ones makes the search of a good CNN architecture a challenging task.We carry out a thorough experimental evaluation deploying and analyzing four distinct CNN models with different depth but similar complexity. We show that even the simplest CNN models greatly improve the results using shallow classifiers. All our experiments have been carried out on the challenging TUMGAID dataset, which contains people in different covariate scenarios (i.e.clothing, shoes, bags).en
dc.identifier.isbn978-3-88579-664-0
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/4656
dc.language.isoen
dc.publisherGesellschaft für Informatik, Bonn
dc.relation.ispartofBIOSIG 2017
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-70
dc.subjectDeep Neural Networks
dc.subjectGait Recognition
dc.subjectOptical Flow
dc.subjectResNet
dc.subject3D-CNN
dc.titleEvaluation of CNN architectures for gait recognition based on optical flow mapsen
gi.citation.endPage258
gi.citation.startPage251
gi.conference.date20.-22. September 2017
gi.conference.locationDarmstadt, Germany
gi.conference.sessiontitleFurther Conference Contributions

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
paper25.pdf
Größe:
255.15 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P270 - BIOSIG 2017 - Proceedings of the 16th International Conference of the Biometrics Special Interest Group