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).
|
(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.
Repository Staff Only: item control page