Forest fire smoke recognition based on convolutional neural network

被引:28
作者
Sun, Xiaofang [1 ]
Sun, Liping [1 ]
Huang, Yinglai [1 ]
机构
[1] Northeast Forestry Univ, Harbin 150040, Peoples R China
基金
中国国家自然科学基金;
关键词
Forest fire smoke; Convolutional neural network; Image classification; Kernel principal component analysis;
D O I
10.1007/s11676-020-01230-7
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Traditional fire smoke detection methods mostly rely on manual algorithm extraction and sensor detection; however, these methods are slow and expensive to achieve discrimination. We proposed an improved convolutional neural network (CNN) to achieve fast analysis. The improved CNN can be used to liberate manpower. The network does not require complicated manual feature extraction to identify forest fire smoke. First, to alleviate the computational pressure and speed up the discrimination efficiency, kernel principal component analysis was performed on the experimental data set. To improve the robustness of the CNN and to avoid overfitting, optimization strategies were applied in multi-convolution kernels and batch normalization to improve loss functions. The experimental analysis shows that the CNN proposed in this study can learn the feature information automatically for smoke images in the early stages of fire automatically with a high recognition rate. As a result, the improved CNN enriches the theory of smoke discrimination in the early stages of a forest fire.
引用
收藏
页码:1921 / 1927
页数:7
相关论文
共 18 条
  • [1] Medical Image Analysis using Convolutional Neural Networks: A Review
    Anwar, Syed Muhammad
    Majid, Muhammad
    Qayyum, Adnan
    Awais, Muhammad
    Alnowami, Majdi
    Khan, Muhammad Khurram
    [J]. JOURNAL OF MEDICAL SYSTEMS, 2018, 42 (11)
  • [2] Multi-column deep neural network for traffic sign classification
    Ciresan, Dan
    Meier, Ueli
    Masci, Jonathan
    Schmidhuber, Juergen
    [J]. NEURAL NETWORKS, 2012, 32 : 333 - 338
  • [3] Facial landmark localization by enhanced convolutional neural network
    Deng, Weihong
    Fang, Yuke
    Xu, Zhenqi
    Hu, Jiani
    [J]. NEUROCOMPUTING, 2018, 273 : 222 - 229
  • [4] Convolutional Neural Network With Data Augmentation for SAR Target Recognition
    Ding, Jun
    Chen, Bo
    Liu, Hongwei
    Huang, Mengyuan
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2016, 13 (03) : 364 - 368
  • [5] Hussein H. A., 2018, TIKRIT J PURE SCI, V23, P134, DOI DOI 10.25130/tjps.23.2018.020
  • [6] Real-time human activity recognition from accelerometer data using Convolutional Neural Networks
    Ignatov, Andrey
    [J]. APPLIED SOFT COMPUTING, 2018, 62 : 915 - 922
  • [7] ImageNet Classification with Deep Convolutional Neural Networks
    Krizhevsky, Alex
    Sutskever, Ilya
    Hinton, Geoffrey E.
    [J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90
  • [8] Matlani P, 2019, ENG TECHNOL APPL SCI, V9, P3939
  • [9] Noise robust sound event classification with convolutional neural network
    Ozer, Ilyas
    Ozer, Zeynep
    Findik, Oguz
    [J]. NEUROCOMPUTING, 2018, 272 : 505 - 512
  • [10] Pandya B, 2018, 2018 4TH INTERNATIONAL CONFERENCE ON INFORMATION MANAGEMENT (ICIM2018), P86, DOI 10.1109/INFOMAN.2018.8392815