• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

基于轻量级卷积神经网络的烟雾识别算法

袁飞 赵绪言 王一戈 赵治晟

袁飞, 赵绪言, 王一戈, 赵治晟. 基于轻量级卷积神经网络的烟雾识别算法[J]. 西南交通大学学报, 2020, 55(5): 1111-1116, 1132. doi: 10.3969/j.issn.0258-2724.20190777
引用本文: 袁飞, 赵绪言, 王一戈, 赵治晟. 基于轻量级卷积神经网络的烟雾识别算法[J]. 西南交通大学学报, 2020, 55(5): 1111-1116, 1132. doi: 10.3969/j.issn.0258-2724.20190777
YUAN Fei, ZHAO Xuyan, WANG Yige, ZHAO Zhisheng. Smoke Recognition Algorithm Based on Lightweight Convolutional Neural Network[J]. Journal of Southwest Jiaotong University, 2020, 55(5): 1111-1116, 1132. doi: 10.3969/j.issn.0258-2724.20190777
Citation: YUAN Fei, ZHAO Xuyan, WANG Yige, ZHAO Zhisheng. Smoke Recognition Algorithm Based on Lightweight Convolutional Neural Network[J]. Journal of Southwest Jiaotong University, 2020, 55(5): 1111-1116, 1132. doi: 10.3969/j.issn.0258-2724.20190777

基于轻量级卷积神经网络的烟雾识别算法

doi: 10.3969/j.issn.0258-2724.20190777
详细信息
    作者简介:

    袁飞(1974—),男,高级工程师,研究方向为交通信息化,E-mail:2672567177@qq.com

  • 中图分类号: V221.3

Smoke Recognition Algorithm Based on Lightweight Convolutional Neural Network

  • 摘要: 由于烟雾图像场景模糊不清,背景复杂多变,难以捕获到有效特征,导致算法识别误报率和漏报率较高;此外,深度卷积神经网络结构复杂,参数繁多,难以缩短其计算时间至1 ms内,这成为实时火灾预警的一大难题. 为了解决上述问题,提出了一种基于4种Inception结构的轻量级卷积神经网络SInception (sequeeze-and-excitation inception)在此基础上加入SE Block (sequeeze-and-excitation block)用于对烟雾特征进行重新分配;同时,为了避免由于训练样本不足引起的过拟合,原始数据集上采用数据增强技术以及生成对抗网络生成更多训练样本,并在后续实验中采用了融合暗通道先验特征的策略. 实验结果表明:该网络在增强的数据集GAN-Aug-YUAN上将识别误报率降为0的同时将准确率提升至99.65%,且计算时间减少到0.26 ms.

     

  • 图 1  5 × 5卷积分解为两个级联3 × 3卷积

    Figure 1.  5 × 5 volume integral solution by two cascaded 3 × 3 convolution

    图 2  3 × 3卷积分解为3 × 1和1 × 3卷积

    Figure 2.  3 × 3 volume integral solution by 3 × 1 and 1 × 3 convolution

    图 3  SE Block结构

    Figure 3.  SE Block structure

    图 4  DCGAN生成图像结果

    Figure 4.  DCGAN image results

    图 5  数据集YUAN中的图像

    Figure 5.  Image in data set YUAN

    表  1  SInception v1结构

    Table  1.   SInception v1 structure

    结构类型窗口大小,步长Inception类型输入尺寸/像素
    卷积层 3 × 3,2 128 × 128 × 3
    卷积层 3 × 3,1 63 × 63 × 32
    卷积层 3 × 3,1 61 × 61 × 32
    最大池化 3 × 3,2 61 × 61 × 64
    卷积层 1 × 1,1 30 × 30 × 64
    卷积层 3 × 3,1 30 × 30 × 80
    最大池化 3 × 3,2 28 × 28 × 192
    Inception IN_A 13 × 13 × 192
    Inception IN_B 13 × 13 × 192
    Inception IN_C 13 × 13 × 256
    Inception IN_D 6 × 6 × 512
    平均池化 6 × 6,1 6 × 6 × 768
    线性层 1 × 1 × 768
    softmax 2
    下载: 导出CSV

    表  2  数据集YUAN中图像分布

    Table  2.   Image distribution in data set YUAN

    数据集烟雾图像/张非烟雾图像/张图像总数/张用途
    SET1 552 831 1383 测试
    SET2 688 817 1505 测试
    SET3 2201 8511 10712 训练
    SET4 2254 8363 10617 训练
    下载: 导出CSV

    表  3  SInception与其他识别算法的性能比较

    Table  3.   Performance comparison between SInception and other recognition algorithms

    模型名称识别率/%准确率/%误报率/%速度/ms
    VGG 95.24 97.85 0.18 3.00
    Res-50 95.80 98.16 0 1.70
    Res-101 96.77 98.61 0 2.70
    Inception v3 96.45 98.3 0.30 3.10
    SInception v1 96.61 98.54 0 0.20
    SInception v2 96.94 98.68 0 0.26
    下载: 导出CSV

    表  4  双模态融合模型的性能比较

    Table  4.   Performance comparison of two-mode fusion model %

    模型名称识别率准确率误报率
    SInception v197.0298.720
    SInception v297.6499.000
    下载: 导出CSV

    表  5  数据扩充实验结果对比

    Table  5.   Experimental results comparison ofdata expansion %

    模型名称数据集识别率准确率误报率
    SInception v1 YUAN 96.61 98.54 0
    Aug-YUAN 98.39 99.31 0
    GAN-Aug-YUAN 99.19 99.65 0
    SInception v2 YUAN 96.94 98.68 0
    Aug-YUAN 98.71 99.44 0
    GAN-Aug-YUAN 99.19 99.65 0
    下载: 导出CSV
  • GUBBI J, MARUSIC S, PALANISWAMI M. Smoke detection in video using wavelets and support vector machines[J]. Fire Safety Journal, 2009, 44(8): 1110-1115. doi: 10.1016/j.firesaf.2009.08.003
    KO B C, KWAK J Y, NAM J Y. Wildfire smoke detection using temporospatial features and random forest classifiers[J]. Optical Engineering, 2012, 51(1): 017208.1-017208.10. doi: 10.1117/1.OE.51.1.017208
    YUAN F. Video-based smoke detection with histogram sequence of LBP and LBPV pyramids[J]. Fire Safety Journal, 2011, 46(3): 132-139. doi: 10.1016/j.firesaf.2011.01.001
    YUAN F, SHI J, XIA X, et al. High-order local ternary patterns with locality preserving projection for smoke detection and image classification[J]. Information Sciences, 2016, 372(C): 225-240.
    GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]: IEEE, 2014: 580-587.
    LAN Z, ZHU Y, HAUPTMANN A G, et al. Deep local video feature for action recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. [S.l.]: IEEE, 2017: 1-7.
    FRIZZI S, KAABI R, BOUCHOUICHA M, et al. Convolutional neural network for video fire and smoke detection[C]//Proceedings of the IECON-42nd Annual Conference of the IEEE Industrial Electronics Society. [S.l.]: IEEE, 2016: 877-882.
    MUHAMMAD K, AHMAD J, MEHMOOD I, et al. Convolutional neural networks based fire detection in surveillance videos[J]. IEEE Access, 2018, 6: 18174-18183. doi: 10.1109/ACCESS.2018.2812835
    HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353. doi: 10.1109/TPAMI.2010.168
    GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Advances in Neural Information Processing Systems. Montreal: [s.n.], 2014: 2672-2680.
    RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J/OL]. Computer Science: Machine Learning, 2015: 1511.06434.1-1511.06434.16, [2019-08-22]. https://arxiv.org/abs/1511.06434
    SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]: IEEE, 2016: 2818-2826.
    SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]: IEEE, 2015: 1-9.
    IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift [J/OL]. Computer Science: Machine Learning, 2015: 1502.03167.1-1502.03167.10, [2019-08-22]. https://arxiv.org/abs/1502.03167.
    HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S.l.]: IEEE, 2018: 7132-7141.
  • 加载中
图(5) / 表(5)
计量
  • 文章访问数:  635
  • HTML全文浏览量:  433
  • PDF下载量:  33
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-08-07
  • 修回日期:  2019-11-19
  • 网络出版日期:  2020-07-07
  • 刊出日期:  2020-10-01

目录

    /

    返回文章
    返回