Multi-View Human Action Recognition using Adaptive Optimization Algorithm with Skeleton Based Graph Neural Networks

Abstract

Recognizing human actions from multi-viewpoint video data is a complex task with applications in various fields, including surveillance, robotics, and human-computer interaction. An innovative approach is presented in this study to Multi-View Human Action Recognition (MV-HAR) using an Adaptive Optimization Algorithm (AOA) combined with a Skeleton-based Graph Neural Network (SGNN). The proposed architecture aims to leverage the complementary information from multiple viewpoints while effectively capturing the temporal and spatial dependencies inherent in human actions. The pre-processing pipeline aligns and fuses skeleton data extracted from different viewpoints, producing a coherent representation of the action across cameras. Each skeleton sequence is transformed into a graph structure, where joints represent nodes and edges encapsulate the relationships between joints over time. This sequence of graphs is then processed by the SGNN, which learns to capture the evolving dynamics of the action through multiple graph convolutional layers. On benchmark datasets, the proposed approach proves effective with an accuracy of 96.8%.