基于深度迁移学习的烟雾识别方法

doi:10.11772/j.issn.1001-9081.2017.11.3176

计算机应用 ›› 2017, Vol. 37 ›› Issue (11): 3176-3181.DOI: 10.11772/j.issn.1001-9081.2017.11.3176

• 第十六届中国机器学习会议(CCML 2017) • 上一篇下一篇

基于深度迁移学习的烟雾识别方法

王文朋¹, 毛文涛^1,2, 何建樑¹, 窦智^1,2

1. 河南师范大学计算机与信息工程学院, 河南新乡 453007;
2. 河南省高校计算智能与数据挖掘工程技术中心, 河南新乡 453007

收稿日期:2017-05-16 修回日期:2017-06-07 出版日期:2017-11-10 发布日期:2017-11-11
通讯作者: 毛文涛
作者简介:王文朋(1989-),男,河南新乡人,硕士研究生,主要研究方向:机器学习、模式识别;毛文涛(1980-),男,河南新乡人,副教授,博士,CCF会员,主要研究领域为机器学习、弱信号检测;何建樑(1993-),男,河南信阳人,硕士研究生,主要研究方向:机器学习、时间序列预测;窦智(1977-),男,河南新乡人,副教授,博士,主要研究方向:图像处理、模式识别。
基金资助:
国家自然科学基金资助项目（U1204609）；河南省高校科技创新人才支持计划（15HASTIT022）；河南省高校青年骨干教师资助计划（2014GGJS-046）；河南师范大学优秀青年科学基金资助项目（14YQ007）；河南省高等学校重点科研项目计划（15A520078）；河南省科技攻关项目（172102210333）。

Smoke recognition based on deep transfer learning

WANG Wenpeng¹, MAO Wentao^1,2, HE Jianliang¹, DOU Zhi^1,2

1. College of Computer and Information Engineering, Henan Normal University, Xinxiang Henan 453007, China;
2. Engineering Technology Research Center for Computing Intelligence and Data Mining of Henan Province, Xinxiang Henan 453007, China

Received:2017-05-16 Revised:2017-06-07 Online:2017-11-10 Published:2017-11-11
Supported by:
This work is partially supported by the National Natural Science Foundation of China (U1204609), the Program for Science & Technology Innovation Talents in University of Henan Province (15HASTIT022), the Funding Scheme of University Young Core Instructors in Henan Province (2014GGJS-046), the Foundation of Henan Normal University for Excellent Young Teachers (14YQ007), the Key Scientific Research Project in University of Henan Province (15A520078), the Key Scientific and Technological Project of Henan Province (172102210333).

摘要/Abstract

摘要： 针对传统的基于传感器和图像特征的烟雾识别方法易被外部环境干扰且识别场景单一，从而造成烟雾识别精度较低，而基于深度学习的识别方法对数据量要求较高，对于烟雾数据缺失或数据来源受限的情况模型识别能力较弱的问题，提出一种基于深度迁移学习的烟雾识别方法。将ImageNet数据集作为源数据，利用VGG-16模型进行基于同构数据下的特征迁移。首先，将所有的图像数据进行预处理，对每张图像作随机变换（随机旋转、剪切、翻转等）；其次，引入VGG-16网络，将其卷积层特征进行迁移，并连接预先使用烟雾数据在VGG-16网络中训练过的全连接层；进而构建出基于迁移学习的深度网络，从而训练得到烟雾识别模型。利用公开数据集以及真实场景烟雾图像进行实验验证，实验结果表明，和现有主流烟雾图像识别方法相比，所提方法有较高的烟雾识别率，实验精度达96%以上。

关键词: 深度学习, 迁移学习, 烟雾识别, 微量数据集

Abstract: For smoke recognition problem, the traditional recognition methods based on sensor and image feature are easily affected by the external environment, which would lead to low recognition precision if the flame scene and type change. The recognition method based on deep learning requires a large amount of data, so the model recognition ability is weak when the smoke data is missing or the data source is restricted. To overcome these drawbacks, a new smoke recognition method based on deep transfer learning was proposed. The main idea was to conduct smoke feature transfer by means of VGG-16 (Visual Geometry Group) model with setting ImageNet dataset as source data. Firstly, all image data were pre-processed, including random rotation, cut and overturn, etc. Secondly, VGG-16 network was introduced to transfer the features in the convolutional layers, and to connect the fully connected layers network pre-trained by smoke data. Finally, the smoke recognition model was achieved. Experiments were conducted on open datasets and real-world smoke images. The experimental results show that the accuracy of the proposed method is higher than those of current smoke image recognition methods, and the accuracy is more than 96%.

Key words: deep learning, transfer learning, smoke recognition, small dataset

中图分类号:

TP391.41

王文朋, 毛文涛, 何建樑, 窦智. 基于深度迁移学习的烟雾识别方法[J]. 计算机应用, 2017, 37(11): 3176-3181.

WANG Wenpeng, MAO Wentao, HE Jianliang, DOU Zhi. Smoke recognition based on deep transfer learning[J]. Journal of Computer Applications, 2017, 37(11): 3176-3181.

参考文献

[1] YIM H,OH S,KIM W.A study on the verification scheme for electrical circuit analysis of fire hazard analysis in nuclear power plant[J]. Journal of the Korean Society of Safety, 2015, 30(3):114-122.
[2] YAMADA M, SHIRATORI S. Smoke sensor using mass controlled layer-by-layer self-assembly of polyelectrolytes films[J]. Sensors and Actuators B:Chemical, 2000, 64(1/2):124-127.
[3] KELLER A, RüEGG M, FORSTER M, et al. Open photoacoustic sensor as smoke detector[J]. Sensors and Actuators B:Chemical, 2005, 104(1):1-7.
[4] CHEON J, LEE J, LEE I, et al. A single-chip CMOS smoke and temperature sensor for an intelligent fire detector[J]. IEEE Sensors Journal, 2009, 9(8):914-921.
[5] YU C, ZHANG Y, FANG J, et al. Video smoke recognition based on optical flow[C]//Proceedings of the 20102nd International Conference on Advanced Computer Control. Piscataway, NJ:IEEE, 2010:16-21.
[6] WANG Y. Smoke recognition based on machine vision[C]//Proceedings of the 2016 International Symposium on Computer, Consumer and Control. Washington, DC:IEEE Computer Society, 2016:668-671.
[7] 庄福振,罗平,何清,等.迁移学习研究进展[J].软件学报, 2015, 26(1):26-39.(ZHUANG F Z, LUO P, HE Q, et al. Survey on transfer learning research[J]. Journal of Software, 2015, 26(1):26-39.)
[8] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252.
[9] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2016-11-20]. http://www.robots.ox.ac.uk:5000/~vgg/publications/2015/Simonyan15/simonyan15.pdf.
[10] LI J, CHENG J H, SHI J Y, et al. Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement[M]//Advances in Computer Science and Information Engineering. Berlin:Springer, 2012:553-558.
[11] CUN Y L, JACKEL L D, BOSER B, et al. Handwritten digit recognition:applications of neural network chips and automatic learning[J]. IEEE Communications Magazine, 1989, 27(11):41-46.
[12] BOUVRIE J. Notes on convolutional neural networks[EB/OL].[2016-11-20]. http://cogprints.org/5869/1/cnn_tutorial.pdf.
[13] PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[14] 饶裕平,柴红玲.林火视频监控中烟识别方法概述[J]. 林业调查规划, 2009,34(1):59-62.(RAO Y P, CHAI H L. A general introduction to a method for smoke recognition in vision monitoring of forest fire[J]. Forest Inventory and Planning, 2009, 34(1):59-62.)
[15] SAHINER B, CHAN H P, PETRICK N, et al. Classification of mass and normal breast tissue:a convolution neural network classifier with spatial domain and texture images[J]. IEEE Transactions on Medical Imaging, 1996, 15(5):598-610.
[16] HUANG Y, TIAN S, SUN X, et al. Forest fire smoke recognition based on gray bit plane technology[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2013, 6(6):309-320.
[17] DAI W, YANG Q, XUE G R, et al. Boosting for transfer learning[C]//Proceedings of the 24th International Conference on Machine Learning. New York:ACM, 2007:193-200.
[18] YANG Q, CHEN Y, XUE G R, et al. Heterogeneous transfer learning for image clustering via the social Web[C]//Proceedings of the 47th Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Stroudsburg, PA:Association for Computational Linguistics, 2009:1-9.
[19] XIE M, JEAN N, BURKE M, et al. Transfer learning from deep features for remote sensing and poverty mapping[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Menlo Park, CA:AAAI Press, 2016:3929-3935.
[20] SONOYAMA S, TAMAKI T, HIRAKAWA T, et al. Transfer learning for endoscopic image classification[EB/OL].[2016-11-20]. http://www.researchgate.net/profile/Tetsushi_Koide/publication/306474619_Transfer_Learning_for_Endoscopic_Image_Classification/links/587af87308ae4445c0630cc7.pdf.

基于深度迁移学习的烟雾识别方法

Smoke recognition based on deep transfer learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[4]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[8]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[9]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[10]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[11]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[12]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[13]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[14]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[15]	史杨潇, 章军, 陈鹏, 王兵. 基于轻量级网络的钢铁表面缺陷分类[J]. 计算机应用, 2021, 41(6): 1836-1841.