首页 > 论文 > 激光与光电子学进展 > 55卷 > 5期(pp:51008--1)

基于并行深度残差网络的堆场烟雾检测方法

Smoke Detection in Storage Yard Based on Parallel Deep Residual Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

堆场烟雾检测对于火灾预警、保障人员与财产安全具有重要意义。针对传统烟雾检测方法特征提取不充分,误报率偏高以及稳健性较差的问题,提出一种基于并行深度残差网络的堆场烟雾检测方法。该方法利用目标场景烟雾RGB图像的R、G、B分量以及图像HSI变换的H、S、I分量构建并行深度残差网络,自适应获得烟雾特征;同时通过样本扩边、负样本强化学习策略来加强模型对类烟物体的判别能力。实验结果表明,该算法能有效降低因类烟物体产生的误报率,且提升了网络的检出率和稳健性。

Abstract

Smoke detection in storage yard has great signification for fire early warning and protecting the safety of personnel and property. To solve the problem of insufficient features extraction, high false positive rates and poor robustness of traditional smoke detection methods, a new method of smoke detection in storage yard based on the parallel deep residual network is proposed. This method builds the parallel deep residual network with R, G, B components of the smoke RGB image and H, S, I components of the HSI transform image to adaptively extract the features. Meanwhile, the discriminant ability for the target like-smoke of the model is enhanced by the strategy including expanding the sample scale and reinforcement learning of the negative samples. The experimental results show that the proposed algorithm can effectively reduce the false positive rate caused by target like smoke and improve the detection rate and robustness of network.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop55.051008

所属栏目:图像处理

基金项目:江苏省研究生培养创新工程(SJLX16_0498)、江苏省政策引导类计划(产学研合作)-前瞻性联合研究项目(BY2016022-32)

收稿日期:2017-10-17

修改稿日期:2017-11-23

网络出版日期:--

作者单位    点击查看

王正来:江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122
黄敏:江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122
朱启兵:江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122
蒋胜:江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122

联系人作者:黄敏(huangmzqb@163.com)

备注:王正来(1993—),男,硕士研究生,主要从事检测与传感技术方面的研究。E-mail: wang930508@163.com

【1】Huang Z H. Brief discussion unit fire safety training[J]. Marine Fire, 2016, 37(5): 15-17.
黄祖华. 浅议单位消防安全培训[J]. 水上消防, 2016, 37(5): 15-17.

【2】Jiang M X, Wang H Y, Cai X Y. Early smoke detection based on codebook model and multiple features[J]. Journal of Image and Graphics, 2012, 17(9): 1102-1108.
姜明新, 王洪玉, 蔡兴洋. 基于码本模型和多特征的早期烟雾检测[J]. 中国图象图形学报, 2012, 17(9): 1102-1108.

【3】Yu C Y, Fang J, Wang J J, et al. Video fire smoke detection using motion and color features[J]. Fire Technology, 2010, 46(3): 651-663.

【4】Yuan F N. Video-based smoke detection with histogram sequence of LBP and LBPV pyramids[J]. Fire Safety Journal, 2011, 46(3): 132-139.

【5】Ho C C. Machine vision-based real-time early flame and smoke detection[J]. Measurement Science and Technology, 2009, 20(4): 045502.

【6】Luo S, Jiang Y Z. State-of-art of video based smoke detection algorithms[J]. Journal of Image and Graphics, 2013, 18(10): 1225-1236.
罗胜, Jiang Yuzheng. 视频检测烟雾的研究现状[J]. 中国图象图形学报, 2013, 18(10): 1225-1236.

【7】Liu F, Liu P Y, Li B, et al. Deep learning model design of video target tracking based on TensorFlow platform[J]. Laser & Optoelectronics Progress, 2017, 54(9): 091501.
刘帆, 刘鹏远, 李兵, 等. TensorFlow平台下的视频目标跟踪深度学习模型设计[J]. 激光与光电子学进展, 2017, 54(9): 091501.

【8】Ye G L, Sun S Y, Gao K J, et al. Nighttime pedestrian detection based on faster region convolution neural network[J]. Laser & Optoelectronics Progress, 2017, 54(8): 081003.
叶国林, 孙韶媛, 高凯珺, 等. 基于加速区域卷积神经网络的夜间行人检测研究[J]. 激光与光电子学进展, 2017, 54(8): 081003.

【9】Krstinic D, Stipanicev D, Jakovcevic T. Histogram-based smoke segmentation in forest fire detection system[J]. Information Technology and Control, 2009, 38(3): 237-244.

【10】Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166.

【11】Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[J]. Journal of Machine Learning Research, 2010, 11(9): 249-256.

【12】He K M, Zhang X Y, Ren S Q, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[C]. 2015 IEEE International Conference on Computer Vision (ICCV), 2015: 1026-1034.

【13】LeCun Y A, Bottou L, Orr G B, et al. Efficient backprop[J]. Neural Networks: Tricks of the Trade, 2012: 9-48.

【14】He K M, Sun J. Convolutional neural networks at constrained time cost[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 5353-5360.

【15】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.

引用该论文

Wang Zhenglai,Huang Min,Zhu Qibing,Jiang Sheng. Smoke Detection in Storage Yard Based on Parallel Deep Residual Network[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051008

王正来,黄敏,朱启兵,蒋胜. 基于并行深度残差网络的堆场烟雾检测方法[J]. 激光与光电子学进展, 2018, 55(5): 051008

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF