现代信息科技2024，Vol.8Issue(22)：20-24,5.DOI:10.19850/j.cnki.2096-4706.2024.22.005
基于自注意力卷积神经网络的吸烟行为识别方法
Smoking Behavior Recognition Method Based on Self-Attention Convolutional Neural Network
摘要
Abstract
Convolutional Neural Network has become the mainstream method in the current visual behavior recognition task because of its powerful feature extraction ability.In order to effectively monitor and warn smoking behavior in public places,this paper proposes a smoking behavior recognition method based on Self-Attention Convolutional Neural Network.By analyzing the key features of smoking behavior in images and videos,an efficient Convolutional Neural Network model is designed.This model can accurately and efficiently extract the key features of images by introducing Self-Attention mechanism to achieve accurate recognition of smoking behavior.The experimental results show that the proposed method has good recognition effect and robustness in different scenarios,and has high practical value.关键词
卷积神经网络/吸烟行为识别/自注意力Key words
Convolutional Neural Network/smoking behavior recognition/Self-Attention分类
信息技术与安全科学引用本文复制引用
方武,连圣阳,落莉莉,李慧姝..基于自注意力卷积神经网络的吸烟行为识别方法[J].现代信息科技,2024,8(22):20-24,5.基金项目
江苏省高等学校基础科学(自然科学)研究面上项目(22KJB140014) （自然科学）
