火力与指挥控制2026，Vol.51Issue(5)：74-81,8.DOI:10.3969/j.issn.1002-0640.2026.05.010
基于异构双流图卷积网络的人体行为识别
Human Behavior Recognition Based on Heterogeneous Dual-stream Graph Convolutional Networks
申皓宇 1黄利 2杜伟伟 3李震1
作者信息
- 1. 北方自动控制技术研究所,太原 030006
- 2. 山西大学计算机与信息技术学院,太原 030006
- 3. 北方自动控制技术研究所,太原 030006||智能信息控制技术山西省重点实验室,太原 030006
- 折叠
摘要
Abstract
Aiming at the urgent demand for real-time and high-precision abnormal behavior recognition in military security scenarios,a heterogeneous dual-stream graph convolutional network is proposed.By decoupling skeletal features into geometric features and coordinate features,a dual-stream network is constructed to process heterogeneous information.An early fusion mechanism is adopted to dynamically integrate features,and a channel bottleneck constraint module is designed to optimize computational efficiency,so as to achieve the optimal balance between accuracy and efficiency and meet the deployment requirements on edge devices.Experimental results demonstrate that the proposed model achieves better performance compared with other mainstream models,and can provide effective solutions for military security applications such as abnormal activity recognition and sentry behavior monitoring in military sites.关键词
行为识别/图卷积神经网络/异构双流分支/通道压缩/军事安防Key words
behavior recognition/graph convolutional neural network/heterogeneous dual stream branch/channel compression/military security分类
信息技术与安全科学引用本文复制引用
申皓宇,黄利,杜伟伟,李震..基于异构双流图卷积网络的人体行为识别[J].火力与指挥控制,2026,51(5):74-81,8.
