摘要
对吸烟者行为的分析研究,是烟草行业创新发展的重要需求。该文结合吸烟室应用场景,提出一种基于视觉的吸烟行为研究方法,构建了基于视觉的吸烟行为数据采集和分析流程,获取包含外观特征、烟包品牌、抽吸行为、人脸情绪在内的6维度吸烟行为数据;设计并实现了基于视觉的吸烟行为数据采集分析系统,系统采用云+端的层次化架构,由智能终端系统、云端服务平台和数据应用系统这3个部分组成。系统应用表明:系统实现了吸烟室内吸烟者在自然状态下的行为识别和数据收集,可为烟草企业认知和了解吸烟者吸烟行为提供有效的数据支持,具有较好的应用价值和实践意义。
The analysis and research of smokers’behavior is an important demand for the innovative development of tobacco industry.Combined with the application scenario of smoking room,this paper proposes a vision-based smoking behavior research method,constructs a vision-based smoking behavior data collection and analysis process,and obtains six dimensions of smoking behavior data including appearance characteristics,cigarette pack brand,smoking behavior,facial emotion.Then,a vision-based analysis system of smoking behavior is designed and implemented.The system adopts the hierarchical structure of cloud and end,which is composed of intelligent terminal system,cloud service platform and data application system.The application results show that the system realizes the automatic recognition and data collection of smoking behavior in the smoking room under the natural state.It can provide effective data support for tobacco enterprises to recognize and understand the smoking behavior of consumers,and has better application value and practical significance.
作者
甘剑
GAN Jian(Information Center,China Tobacco Hunan Industrial Co.,Ltd.,Changsha,Hunan Province,410019 China)
出处
《科技资讯》
2023年第1期233-236,250,共5页
Science & Technology Information
关键词
吸烟者
吸烟行为
数据采集分析
智能图像识别
Cigarette consumers
Smoking behavior
Data collection and analysis
Intelligent image recognition