Action Recognition via Graph Convolutional Networks for the Assisted Living of the Elderly

• Main Authors: Tsakiris, Zois, Tsochatzidis, Lazaros, Pratikakis, Ioannis, Menychtas, Dimitrios, Aggelousis, Nikolaos
• Format: Conference Proceeding
• Language: English
• Subjects: Assisted living; Conferences; Focusing; Graph convolutional networks; Medical conditions; Nanoscale devices; Pain; Skeleton-based action recognition
• ISSN: 2165-0179
• DOI: 10.1109/CNNA60945.2023.10652618

Automated monitoring systems can play a crucial role in the effective assisted living of the elderly. Such systems aim to detect specific actions or activities of the individual which may indicate discomfort, pain or danger. Towards this end, we employ a skeleton-based representation for the human body, as a graph of interconnected nodes, that can be used as the means of meaningful spatial-temporal information of an action. In this paper, a novel methodology for human action recognition is proposed in the context of Graph Convolutional Networks that, along with the conventional full-body human graph, utilizes an arm-specific graph representation to better capture the fine-grained motion of the arms. For experimental evaluation, a new dataset is created that comprises a variety of actions, performed by multiple elderly individuals, specifically for the purpose of monitoring everyday life activities. Additionally, experimentation is extended to a well-established large dataset, namely NTU RGB+D 120, focusing on the actions that correspond to medical conditions. Experimental results demonstrate the effectiveness of our combined approach, compared to the single graph approach, in terms of recognition accuracy.