• 《工程索引》(EI)刊源期刊
  • 综合性科学技术类中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于TATLNet的输电场景威胁检测

李梅 郭飞 张立中 王波 张俊岭 李兆桐

李梅, 郭飞, 张立中, 王波, 张俊岭, 李兆桐. 基于TATLNet的输电场景威胁检测[J]. 工程科学学报, 2020, 42(4): 509-515. doi: 10.13374/j.issn2095-9389.2019.09.15.004
引用本文: 李梅, 郭飞, 张立中, 王波, 张俊岭, 李兆桐. 基于TATLNet的输电场景威胁检测[J]. 工程科学学报, 2020, 42(4): 509-515. doi: 10.13374/j.issn2095-9389.2019.09.15.004
LI Mei, GUO Fei, ZHANG Li-zhong, WANG Bo, ZHANG Jun-ling, LI Zhao-tong. Threat detection in transmission scenario based on TATLNet[J]. Chinese Journal of Engineering, 2020, 42(4): 509-515. doi: 10.13374/j.issn2095-9389.2019.09.15.004
Citation: LI Mei, GUO Fei, ZHANG Li-zhong, WANG Bo, ZHANG Jun-ling, LI Zhao-tong. Threat detection in transmission scenario based on TATLNet[J]. Chinese Journal of Engineering, 2020, 42(4): 509-515. doi: 10.13374/j.issn2095-9389.2019.09.15.004

基于TATLNet的输电场景威胁检测

doi: 10.13374/j.issn2095-9389.2019.09.15.004
基金项目: 国家重点研发计划资助项目(2017ZX05013-002);山东省自然基金资助项目(ZR2019MF049)
详细信息
    通讯作者:

    E-mail: s18070027@s.upc.edu.cn

  • 中图分类号: TP277

Threat detection in transmission scenario based on TATLNet

More Information
  • 摘要: 在输电场景中,吊车等大型机械的运作会威胁到输电线路的安全。针对此问题,从训练数据、网络结构和算法超参数的角度进行研究,设计了一种新的端到端的输电线路威胁检测网络结构TATLNet,其中包括可疑区域生成网络VRGNet和威胁判别网络VTCNet,VRGNet与VTCNet共享部分卷积网络以实现特征共享,并利用模型压缩的方式压缩模型体积,提升检测效率,从计算机视觉和系统工程的角度对入侵输电场景的大型机械进行精确预警。针对训练数据偏少的问题,利用多种数据增强技术相结合的方式对数据集进行扩充。通过充分的试验对本方法的多个超参数进行探究,综合检测准确率和推理速度来研究其最优配置。研究结果表明,随着网格数目的增加,准确率也随之增加,而召回率有先增加后降低的趋势,检测效率则随着网格的增加迅速降低。综合检测准确率与推理速度,确定9×9为最优网格划分方案;随着输入图像尺寸的增加,检测准确率稳步上升而检测效率逐渐下降,综合检测准确率和效率,选择480×480像素作为最终的图像输入尺寸。输入实验以及现场部署表明,相对于其他的轻量级目标检测算法,该方法对输电现场入侵的吊车等大型机械的检测具有更优秀的准确性和效率,满足实际应用的需要。
  • 图  1  系统流程图

    Figure  1.  System flow chart

    图  2  数据增强图像。(a) GAN生成图像;(b)椒盐噪声图像

    Figure  2.  Images from data enhancement: (a)image generated from GAN; (b) image with salt and pepper noise

    图  3  TATLNet结构图

    Figure  3.  Structure of TATLNet

    图  4  VRGNet结构图

    Figure  4.  Structure of VRGNet

    图  5  VTCNet结构图

    Figure  5.  Structure of VTCNet

    图  6  实地部署检测效果

    Figure  6.  Detection result in field deployment

    表  1  VRGNet中网格划分对检测结果的影响

    Table  1.   Different strategies of grid cells partitioning

    GridsPrecision/%Recall/%Efficiency/ms
    2×272.2368.4933.61
    3×384.8071.9935.85
    4×489.6079.5936.48
    5×584.3783.8740.37
    6×688.4886.9045.62
    8×892.6290.1447.66
    9×995.1992.4051.63
    10×1093.2895.1567.21
    12×1281.1484.368.29
    14×1475.6184.497.29
    15×1575.1186.306.05
    下载: 导出CSV

    表  2  数据增强效果

    Table  2.   Effect of data enhancement %

    Data enhancement methodsPrecisionRecall
    Original images78.1971.52
    Traditional methods85.7381.35
    GAN93.6290.55
    GAN+traditional methos95.1992.40
    下载: 导出CSV

    表  3  不同输入图像尺寸的比较

    Table  3.   Comparison of different image scales

    Image scalesPrecision/%Recall/%Efficiency/ms
    240×24064.7159.3230.75
    320×32068.5564.0839.65
    416×41680.2481.4647.39
    480×48095.1992.4051.63
    640×64092.1095.14185.19
    960×96095.1495.72486.49
    下载: 导出CSV

    表  4  与其他方法的比较

    Table  4.   Comparison with other methods

    MethodsPrecision/%Recall/%Efficiency/ms
    TATLNet94.6892.4051.63
    MobileNet88.3582.4767.48
    ShuffleNet83.6584.9158.78
    Uncompressed TATLNet95.1993.15253.64
    下载: 导出CSV

    表  5  现场部署检测统计

    Table  5.   Detection statistics in field deployment

    AlarmsActual number of intrusionsCorrect alarmsPrecision/%Recall/%Efficiency/ms
    79767493.6797.3796.10
    下载: 导出CSV
  • [1] Minker G A. Transmission Line Safety Monitoring System: U.S. Patent, 6377184. 2002-4-23
    [2] 罗霞, 张良勇, 罗文金, 等. 基于热释电红外传感器的无人机巡检控制系统研究. 科技经济导刊, 2019, 27(8):3

    Luo X, Zhang L Y, Luo W J, et al. Research on UAV patrol control system based on pyroelectric infrared sensor. Technol Econom Guide, 2019, 27(8): 3
    [3] Lu Y X, Kumar A, Zhai S F, et al. Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017: 5334
    [4] He Y H, Zhang X Y, Sun J. Channel pruning for accelerating very deep neural networks // Proceedings of the IEEE International Conference on Computer Vision. Venice, 2017: 1389
    [5] Han S, Mao H Z, Dally W J. Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding[J/OL]. arXiv preprint (2016-02-15)[2019-09-15]. https://arxiv.org/abs/1510.00149
    [6] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets // Advances in Neural Information Processing Systems. Montreal, 2014: 2672
    [7] 段树忠, 魏可强. 输电线路主动预警式防外力破坏监控系统研究. 城市建设理论研究, 2017(15):6

    Duan S Z, Wei K Q. Research on active early warning monitoring system for preventing external force damage of transmission lines. Theor Res Urban Constr, 2017(15): 6
    [8] 郭圣, 曾懿辉, 张纪宾, 等. 输电线路防外力破坏智能监控系统的应用. 广东电力, 2018, 31(4):139

    Guo S, Zeng Y H, Zhang J B, et al. Application of intelligent monitoring system for external force damage prevention for transmission lines. Guangdong Electr Power, 2018, 31(4): 139
    [9] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436 doi: 10.1038/nature14539
    [10] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks // Advances in Neural Information Processing Systems. Lake Tahoe, 2012: 1097
    [11] Papageorgiou C P, Oren M, Poggio T. A general framework for object detection // Sixth International Conference on Computer Vision. Tampa, 1998: 555
    [12] Jiao L, Zhang F, Liu F, et al. A survey of deep learning-based object detection. IEEE Access, 2019(7): 128837
    [13] Zou Z, Shi Z, Guo Y, et al Object detection in 20 years: a survey[J/OL]. arXiv preprint (2019-05-13)[2019-09-15]. https://arxiv.org/abs/1905.05241
    [14] Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector // European Conference on Computer Vision. Amsterdam, 2016: 21
    [15] Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Amsterdam, 2016: 779
    [16] Law H, Deng J. CornerNet: detecting objects as paired keypoints // Proceedings of the European Conference on Computer Vision. Munich, 2018: 734
    [17] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, 2014: 580
    [18] Girshick R. Fast R-CNN // Proceedings of the IEEE International Conference on Computer Vision. Santiago, 2015: 1440
    [19] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks // Advances in Neural Information Processing Systems. Montreal, 2015: 91
    [20] He K M, Gkioxari G, Dollár P, et al. Mask R-CNN // Proceedings of the IEEE International Conference on Computer Vision. Honolulu, 2017: 2961
    [21] Huang R, Pedoeem J, Chen C X. YOLO-LITE: a real-time object detection algorithm optimized for non-GPU computers // 2018 IEEE International Conference on Big Data (Big Data). Seattle, 2018: 2503
    [22] Howard A G, Zhu M, Chen B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J/OL]. arXiv preprint (2017-04-17)[2019-09-15]. https://arxiv.org/abs/1704.04861
    [23] Zhang X Y, Zhou X Y, Lin M X, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 6848
    [24] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[J/OL]. arXiv preprint (2016-01-07)[2019-09-15]. https://arxiv.org/abs/1511.06434
    [25] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017: 2117
  • 加载中
图(6) / 表(5)
计量
  • 文章访问数:  570
  • HTML全文浏览量:  605
  • PDF下载量:  10
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-09-15
  • 刊出日期:  2020-04-01

目录

    /

    返回文章
    返回