arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.16638cs.CVcs.AI
收藏

基于参数优化多阶段图卷积网络与Transformer模型的特征融合人体行为识别

Feature Fusion for Human Activity Recognition using Parameter-Optimized Multi-Stage Graph Convolutional Network and Transformer Models

Khalifa University of Science and Technology(哈利法科学技术大学);Abu Dhabi University(阿布扎比大学)

Mohammad Belal, Taimur Hassan, Abdelfatah Ahmed, Ahmad Aljarah, Nael Alsheikh, Irfan Hussain

AI总结:

本研究针对人体行为识别任务,提出结合PO-MS-GCN与Transformer的特征融合方法,在四个公开数据集上验证了其有效性,且PO-MS-GCN性能优于现有最优模型。

摘要:

人体行为识别(HAR)是借助计算机与机器视觉技术理解人类动作的关键研究领域。深度学习已成为该任务的有力工具,卷积神经网络(CNNs)、Transformer等模型被用于捕捉人体运动的多维度特征。本研究的核心贡献之一是验证了特征融合可通过捕捉时空特征提升HAR准确率,这对开发更精准、鲁棒的行为识别系统具有重要意义。研究使用HuGaDB、PKU-MMD、LARa、TUG四个数据集的传感器数据,训练并评估了PO-MS-GCN(参数优化多阶段图卷积网络)与Transformer两种模型,其中PO-MS-GCN性能优于现有最优模型。HuGaDB与TUG数据集上取得了高准确率与F1值,LARa与PKU-MMD数据集得分较低,特征融合在所有数据集上均提升了识别效果。

英文摘要:

Human activity recognition (HAR) is a crucial area of research that involves understanding human movements using computer and machine vision technology. Deep learning has emerged as a powerful tool for this task, with models such as Convolutional Neural Networks (CNNs) and Transformers being employed to capture various aspects of human motion. One of the key contributions of this work is the demonstration of the effectiveness of feature fusion in improving HAR accuracy by capturing spatial and temporal features, which has important implications for the development of more accurate and robust activity recognition systems. The study uses sensory data from HuGaDB, PKU-MMD, LARa, and TUG datasets. Two model, the PO-MS-GCN and a Transformer were trained and evaluated, with PO-MS-GCN outperforming state-of-the-art models. HuGaDB and TUG achieved high accuracies and f1-scores, while LARa and PKU-MMD had lower scores. Feature fusion improved results across datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑