A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data

e-Archivo Repository

Show simple item record

dc.contributor.author Hieu Pham, Huy
dc.contributor.author Salmane, Houssam
dc.contributor.author Khoudour, Louahdi
dc.contributor.author Crouzil, Alain
dc.contributor.author Zegers, Pablo
dc.contributor.author Velastin Carroza, Sergio Alejandro
dc.date.accessioned 2019-09-26T08:16:08Z
dc.date.available 2019-09-26T08:16:08Z
dc.date.issued 2019-08-27
dc.identifier.bibliographicCitation Pham, H.H., Salmane, H., Khoudour, L., Crouzil, A., Zegers, P. y Velastin, S.A. (2019). A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data. In International Conference on Image Analysis and Recognition, 11662, pp 18-32.
dc.identifier.isbn 978-3-030-27201-2
dc.identifier.uri http://hdl.handle.net/10016/28906
dc.description This paper has been published at the Proceedings of 16th International Conference on Image Analysis and Recognition
dc.description Contains Supplementary material
dc.description.abstract We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and their motions into a single RGB image. An Adaptive Histogram Equalization (AHE) algorithm is then applied on the color images to enhance their local patterns and generate more discriminative features. For learning and classification tasks, we design Deep Neural Networks based on the Densely Connected Convolutional Architecture (DenseNet) to extract features from enhanced-color images and classify them into classes. Experimental results on two challenging datasets show that the proposed method reaches state-of-the-art accuracy, whilst requiring low computational time for training and inference. This paper also introduces CEMEST, a new RGB-D dataset depicting passenger behaviors in public transport. It consists of 203 untrimmed real-world surveillance videos of realistic normal and anomalous events. We achieve promising results on real conditions of this dataset with the support of data augmentation and transfer learning techniques. This enables the construction of real-world applications based on deep learning for enhancing monitoring and security in public transport.
dc.description.sponsorship This research was supported by the Cerema, France. Sergio A. Velastin is grateful for funding from the Universidad Carlos III de Madrid, the EU’s 7th Framework Programme for Research, Technological Development and demonstration (grant 600371), Ministerio de Economia, Industria y Competitividad (COFUND2013- 51509), Ministerio de Educación, cultura y Deporte (CEI-15-17) and Banco Santander.
dc.format.extent 21
dc.language.iso eng
dc.publisher Springer
dc.rights © Springer Nature Switzerland AG 2019
dc.subject.other Action recognition
dc.subject.other Skeletal data
dc.subject.other Enhanced-spmf
dc.subject.other Densenet
dc.title A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data
dc.type bookPart
dc.type conferenceObject
dc.subject.eciencia Informática
dc.identifier.doi https://doi.org/10.1007/978-3-030-27202-9_2
dc.rights.accessRights openAccess
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/600371
dc.relation.projectID Gobierno de España. COFUND2013-51509
dc.relation.projectID Gobierno de España. CEI-15-17
dc.type.version acceptedVersion
dc.relation.eventdate 27-29 August 2019
dc.relation.eventplace Waterloo, Ontario, Canada
dc.relation.eventtitle 16th International Conference on Image Analysis and Recognition (ICIAR 2019)
dc.relation.eventtype proceeding
dc.identifier.publicationfirstpage 18
dc.identifier.publicationlastpage 32
dc.identifier.publicationtitle Image Analysis and Recognition
dc.identifier.publicationvolume 11662
dc.identifier.uxxi CC/0000029968
dc.contributor.funder European Commission
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.contributor.funder Ministerio de Educación, Cultura y Deporte (España)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record