OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

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

Pham, Huy-Hieu and Salmane, Houssam and Khoudour, Louahdi and Crouzil, Alain and Zegers, Pablo and Velastin, Sergio A. A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data. (2019) In: 16th International Conference on Image Analysis and Recognition (ICIAR 2019can), 27 August 2019 - 29 August 2019 (Waterloo, Canada).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
978kB

Official URL: https://doi.org/10.1007/978-3-030-27202-9_2

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 en- code 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. Experi- mental 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.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Thanks to Springer editor. This papers appears in volume 11662 of Lecture Notes in Computer Science ISSN : 0302-9743 ISBN 978-3-030-27201-2 The original PDF is available at: https://link.springer.com/chapter/10.1007/978-3-030-27202-9_2
HAL Id:hal-02883879
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Aparnix (CHILE)
Other partners > Centre d'études et d'expertise sur les risques, l'environnement, la mobilité et l'aménagement - CEREMA (FRANCE)
Other partners > Cortexica Vision Systems (UNITED KINGDOM)
Other partners > Queen Mary University of London - QMUL (UNITED KINGDOM)
Other partners > Universidad Carlos III de Madrid - UC3M (SPAIN)
Laboratory name:
Funders:
Cerema (France) - FP7 funding programme, Universidad Carlos III de Madrid (Europe) - Ministerio de Economia, Industria y Competitividad - Ministerio de Educacion, cultura y Deporte (Espagne) - Banco Santander (Espagne)
Statistics:download
Deposited On:29 Jun 2020 12:44

Repository Staff Only: item control page