模式识别与人工智能
2025年4月3日 星期四   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2021, Vol. 34 Issue (9): 844-852    DOI: 10.16451/j.cnki.issn1003-6059.202109007
“深度学习算法及在图像与视觉的应用”专题 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于双通道深度CNN的烟雾浓度测量方法
莫鸿飞1, 谢振平1,2
1.江南大学 人工智能与计算机学院 无锡 214122
2.江南大学 江苏省媒体设计与软件技术重点实验室 无锡 214122
Smoke Density Measurement Method Based on Dual-Channel Deep CNN
MO Hongfei1, XIE Zhenping1,2
1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122
2. Jiangsu Key Laboratory of Media Design and Software Technology, Jiangnan University, Wuxi 214122

全文: PDF (1166 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 现有基于视频图像测量烟雾浓度的方法主要通过人工提取特征,需要已知环境的大气光、背景等外界条件.为了提高烟雾浓度测量方法的直接性和实用性,文中通过烟雾化方程,建立烟雾图像与其浓度数值的对应关系,进而提出基于双通道深度卷积神经网络(DCCNN)的烟雾浓度测量方法,实现端到端的烟雾浓度直接测量.DCCNN中采用1×1卷积进行通道数据融合,引入跳跃连接解决网络层数较深时梯度消失问题,加快训练过程.同时引入自注意力机制,自动学习隐含特征的重要程度,再合并两个通道提取的特征,获得综合测量结果.实验表明,DCCNN测量烟雾浓度的平均绝对误差较低,综合性能较优.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
莫鸿飞
谢振平
关键词 烟雾浓度深度卷积神经网络深度学习烟雾化方程注意力机制    
Abstract:In the existing methods for measuring smoke density based on video images, features are mainly extracted manually, and the external conditions, such as ambient light and background, are required as known conditions. To improve the directness and practicability of the smoke density measurement method, the corresponding relationship between smoke images and their density values is established through the Aerosolization equation. The smoke density dataset is established as well. A smoke density measurement method based on dual-channel deep convolution neural network(DCCNN) is proposed to realize the end-to-end direct measurement of smoke density. In DCCNN, 1×1 convolution is used for channel data fusion, and jump connection is introduced to make the neural network training faster. The self-attention mechanism is also introduced to learn the importance of hidden features automatically. Finally, the features extracted from two channels are combined to obtain comprehensive measurement results. Experiments show that DCCNN gains lower mean absolute error and higher comprehensive performance.
Key wordsSmoke Density    Deep Convolutional Neural Network    Deep Learning    Aerosolization Equation    Attention Mechanism   
收稿日期: 2021-04-30     
ZTFLH: TP 391.4  
基金资助:国家自然科学基金项目(No.61872166)、江苏省“六大人才高峰”项目(No.XYDXX-161)资助
通讯作者: 谢振平,博士,教授,主要研究方向为知识建模、认知学习.E-mail:xiezp@jiangnan.edu.cn.   
作者简介: 莫鸿飞,硕士研究生, 主要研究方向为计算机视觉.E-mail:1640657648@qq.com.
引用本文:   
莫鸿飞, 谢振平. 基于双通道深度CNN的烟雾浓度测量方法[J]. 模式识别与人工智能, 2021, 34(9): 844-852. MO Hongfei, XIE Zhenping. Smoke Density Measurement Method Based on Dual-Channel Deep CNN. , 2021, 34(9): 844-852.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202109007      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I9/844
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn