高级搜索

基于深度学习的绝缘子定向识别算法

李彩林 张青华 陈文贺 江晓斌 袁斌 杨长磊

引用本文: 李彩林, 张青华, 陈文贺, 江晓斌, 袁斌, 杨长磊. 基于深度学习的绝缘子定向识别算法[J]. 电子与信息学报, doi: 10.11999/JEIT190350 shu
Citation:  Cailin LI, Qinghua ZHANG, Wenhe CHEN, Xiaobin JIANG, Bin YUAN, Changlei YANG. Insulator Orientation Detection Based on Deep Learning[J]. Journal of Electronics and Information Technology, doi: 10.11999/JEIT190350 shu

基于深度学习的绝缘子定向识别算法

    作者简介: 李彩林: 男,1985年生,副教授,研究方向为数字摄影测量与计算机视觉;
    张青华: 男,1992年生,硕士,研究方向为深度学习目标检测、计算机视觉;
    陈文贺: 男,1992年生,硕士,研究方向为深度学习目标识别;
    江晓斌: 男,1994年生,硕士,研究方向为点云3维重建;
    袁斌: 女,1995年生,硕士,研究方向为倾斜摄影测量;
    杨长磊: 男,1995年生硕士,研究方向为深度学习在农业遥感中的应用
    通讯作者: 张青华,zhangqinghuamail@163.com
  • 基金项目: 国家自然科学基金(41601496, 41701525);山东省重点研发计划(2018GGX106002);山东省自然科学基金(ZR2017LD002);山东理工大学齐文化研究专项(2017QWH032)

摘要: 为了解决绝缘子目标检测中无法精确定位的问题,该文基于深度学习提出一种绝缘子定向识别算法,通过在轴对齐检测框中加入角度信息,可有效解决常规深度学习算法无法精确定位目标的问题。该算法首先将角度旋转参数引入轴对齐矩形检测框中构成定向检测框,然后将该参数偏移量作为第5参数加入到损失函数中进行迭代回归,同时为提高检测精度在训练过程中使用Adam算法替代随机梯度下降(SGD)算法进行损失函数优化,最终可获得绝缘子定向检测模型。实验分析表明,加入旋转角度的定向检测框可有效对绝缘子目标进行精确定位。

English

    1. [1]

      BARTON J P and INFIELD D G. Energy storage and its use with intermittent renewable energy[J]. IEEE Transactions on Energy Conversion, 2004, 19(2): 441–448. doi: 10.1109/tec.2003.822305

    2. [2]

      WANG Jiafu, LIANG Xidong, and GAO Yanfeng. Failure analysis of decay-like fracture of composite insulator[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2014, 21(6): 2503–2511. doi: 10.1109/tdei.2014.004485

    3. [3]

      GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. 2014 IEEE Conference on Computer Vision and Pattern Recogni-tion, Columbus, USA, 2014: 580–587.

    4. [4]

      GIRSHICK R. Fast R-CNN[C]. 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 1440–1448. doi: 10.1109/ICCV.2015.169.

    5. [5]

      REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]. The 28th Interna-tional Conference on Neural Information Processing Systems, Montreal, Canada, 2015: 91–99.

    6. [6]

      HE Kaiming, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]. 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2980–2988. doi: 10.1109/ICCV.2017.322.

    7. [7]

      REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 779–788. doi: 10.1109/CVPR.2016.91.

    8. [8]

      REDMON J and FARHADI A. YOLO9000: Better, faster, stronger[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 6517–6525.

    9. [9]

      REDMON J and FARHADI A. Yolov3: An incremental improvement[J]. arXiv:1804.02767, 2018.

    10. [10]

      LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: Single shot MultiBox detector[C]. The 14th European Conference on Computer Vision, Amsterdam, the Netherlands, 2016: 21–37. doi: 10.1007/978-3-319-46448-0_2.

    11. [11]

      FU Chengyang, LIU Wei, RANGA A, et al. DSSD: Deconvolutional single shot detector[J]. arXiv:1701.06659, 2017.

    12. [12]

      陈庆, 闫斌, 叶润, 等. 航拍绝缘子卷积神经网络检测及自爆识别研究[J]. 电子测量与仪器学报, 2017, 31(6): 942–953. doi: 10.13382/j.jemi.2017.06.018
      CHEN Qing, YAN Bin, YE Run, et al. Insulator detection and recognition of explosion fault based on convolutional neural networks[J]. Journal of Electronic Measurement and Instrumentation, 2017, 31(6): 942–953. doi: 10.13382/j.jemi.2017.06.018

    13. [13]

      LING Zenan, QIU R C, JIN Zhijian, et al. An accurate and real-time self-blast glass insulator location method based on faster R-CNN and U-net with aerial images[J]. arXiv:1801.05143, 2018.

    14. [14]

      RONNEBERGER O, FISCHER P, and BROX T. U-net: Convolutional networks for biomedical image segmentation[C]. The 18th International Conference on Medical Image Computing and Computer-assisted Intervention, Munich, Germany, 2015: 234–241.

    15. [15]

      ZHAO Zhenbing, FAN Xiaoqing, XU Guozhi, et al. Aggregating deep convolutional feature maps for insulator detection in infrared images[J]. IEEE Access, 2017, 5: 21831–21839. doi: 10.1109/ACCESS.2017.2757030

    16. [16]

      陈文贺, 李彩林, 袁斌, 等. 有效的绝缘子自爆缺陷定位方法[J]. 计算机工程与设计, 2019, 40(8): 2346–2352. doi: 10.16208/j.issn1000-7024.2019.08.041
      CHEN Wenhe, LI Cailin, YUAN Bin, et al. Effective method to locate the self-explosion defect of insulators[J]. Computer Engineering and Design, 2019, 40(8): 2346–2352. doi: 10.16208/j.issn1000-7024.2019.08.041

    17. [17]

      黄新波, 刘新慧, 张烨, 等. 基于红蓝色差和改进K-means算法的航拍绝缘子分类识别方法[J]. 高电压技术, 2018, 44(5): 1528–1534. doi: 10.13336/j.1003-6520.hve.20180430018
      HUANG Xinbo, LIU Xinhui, ZHANG Ye, et al. Classi-fication recognition method of insulator in aerial image based on the red-blue difference and developed K-means algorithm[J]. High Voltage Engineering, 2018, 44(5): 1528–1534. doi: 10.13336/j.1003-6520.hve.20180430018

    18. [18]

      CHEN Chaoyue, GONG Weiguo, HU Yan, et al. Learning oriented region-based convolutional neural networks for building detection in satellite remote sensing images[C]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Han-nover, Germany, 2017: 461–464. doi: 10.5194/isprs-archives-XLII-1-W1-461-2017.

    19. [19]

      DENG Zhipeng, SUN Hao, ZHOU Shilin, et al. Toward fast and accurate vehicle detection in aerial images using coupled region-based convolutional neural networks[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(8): 3652–3664. doi: 10.1109/JSTARS.2017.2694890

    20. [20]

      HE Tong, HUANG Weilin, QIAO Yu, et al. Accurate text localization in natural image with cascaded convolutional text network[J]. arXiv:1603.09423, 2016.

    21. [21]

      YAO Cong, BAI Xiang, SANG Nong, et al. Scene text detection via holistic, multi-channel prediction[J]. arXiv:1606.09002, 2016.

    22. [22]

      ZHANG Zheng, ZHANG Chengquan, SHEN Wei, et al. Multi-oriented text detection with fully convolutional networks[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 4159–4167. doi: 10.1109/CVPR.2016.451.

    23. [23]

      LONG J, SHELHAMER E, DARRELL T. Fully convolu-tional networks for semantic segmentation[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 3431–3440. doi: 10.1109/CVPR.2015.7298965.

    24. [24]

      MA Jianqi, SHAO Weiyuan, Ye Hao, et al. Arbitrary-oriented scene text detection via rotation proposals[J]. IEEE Transactions on Multimedia, 2018, 20(11): 3111–3122. doi: 10.1109/TMM.2018.2818020

    25. [25]

      TANG Tianyu, ZHOU Shilin, DENG Zhipeng, et al. Arbitrary-oriented vehicle detection in aerial imagery with single convolutional neural networks[J]. Remote Sensing, 2017, 9(11): 1170. doi: 10.3390/rs9111170

    26. [26]

      LIU Lei, PAN Zongxu, LEI Bin. Learning a rotation invariant detector with rotatable bounding box[J]. arXiv:1711.09405, 2017.

    27. [27]

      ZHAO Zhenbing, LIU Ning, and WANG Le. Localization of multiple insulators by orientation angle detection and binary shape prior knowledge[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2015, 22(6): 3421–3428. doi: 10.1109/tdei.2015.004741

    28. [28]

      KINGMA D P and BA J. Adam: A method for stochastic optimization[J]. arXiv:1412.6980, 2014.

    29. [29]

      DAI Jifeng, LI Yi, HE Kaiming, et al. R-FCN: Object detection via region-based fully convolutional net-works[C]. The 30th International Con-ference on Neural Information Processing systems, Bar-celona, Spain, 2016: 379–387.

    1. [1]

      张淑军, 张群, 李辉. 基于深度学习的手语识别综述. 电子与信息学报,

    2. [2]

      孙锐, 张广海, 高隽. 基于深度分层特征表示的行人识别方法. 电子与信息学报,

    3. [3]

      王星, 周一鹏, 周东青, 陈忠辉, 田元荣. 基于深度置信网络和双谱对角切片的低截获概率雷达信号识别. 电子与信息学报,

    4. [4]

      程帅, 孙俊喜, 曹永刚, 刘广文, 韩广良. 多示例深度学习目标跟踪. 电子与信息学报,

    5. [5]

      冯浩, 黄坤, 李晶, 高榕, 刘东华, 宋成芳. 基于深度学习的混合兴趣点推荐算法. 电子与信息学报,

    6. [6]

      文成林, 吕菲亚. 基于深度学习的故障诊断方法综述. 电子与信息学报,

    7. [7]

      陈鸿昶, 吴彦丞, 李邵梅, 高超. 基于行人属性分级识别的行人再识别. 电子与信息学报,

    8. [8]

      程帅, 曹永刚, 孙俊喜, 赵立荣, 刘广文, 韩广良. 基于增强群跟踪器和深度学习的目标跟踪. 电子与信息学报,

    9. [9]

      董书琴, 张斌. 基于深度特征学习的网络流量异常检测方法. 电子与信息学报,

    10. [10]

      孙志军, 薛磊, 许阳明. 基于深度学习的边际Fisher分析特征提取算法. 电子与信息学报,

    11. [11]

      李寰宇, 毕笃彦, 杨源, 查宇飞, 覃兵, 张立朝. 基于深度特征表达与学习的视觉跟踪算法研究. 电子与信息学报,

    12. [12]

      智洪欣, 于洪涛, 李邵梅, 高超, 王艳川. 一种基于深度度量学习的视频分类方法. 电子与信息学报,

    13. [13]

      王勇, 吴金君, 田增山, 周牧, 王沙沙. 基于FMCW雷达的多维参数手势识别算法. 电子与信息学报,

    14. [14]

      谢湘, 张立强, 王晶. 残差网络在婴幼儿哭声识别中的应用. 电子与信息学报,

    15. [15]

      徐莹莹, 沈红斌. 基于模式识别的生物医学图像处理研究现状. 电子与信息学报,

    16. [16]

      郭立民, 寇韵涵, 陈涛, 张明. 基于栈式稀疏自编码器的低信噪比下低截获概率雷达信号调制类型识别. 电子与信息学报,

    17. [17]

      徐昊玮, 廉保旺, 邹晓军, 岳哲, 吴鹏. 基于视觉物体识别的抗差岭估计定位算法. 电子与信息学报,

    18. [18]

      侯志强, 戴铂, 胡丹, 余旺盛, 陈晨, 范舜奕. 基于感知深度神经网络的视觉跟踪. 电子与信息学报,

    19. [19]

      侯志强, 王鑫, 余旺盛, 戴铂, 金泽芬芬. 基于自适应深度稀疏网络的在线跟踪算法. 电子与信息学报,

    20. [20]

      杨宏宇, 王峰岩. 基于深度卷积神经网络的气象雷达噪声图像语义分割方法. 电子与信息学报,

  • 图 1  绝缘子定向识别网络结构

    图 2  VGG-16基础网络结构图

    图 3  绝缘子定向识别算法训练流程图

    图 4  旋转角定义示意图

    图 5  轴对齐矩形框交并集示意图

    图 6  倾斜矩形框转化示意图

    图 7  训练损失曲线图

    图 8  测试影像 P-R 曲线图

    图 9  绝缘子定向识别算法测试结果图

    图 10  原始SSD轴对齐矩形框缺点

    图 11  定向矩形框优点

    图 12  扩展目标检测结果

    表 1  训练参数设定

    参数名称参数值
    初始学习率0.0001
    学习率策略Multistep
    批处理大小2
    最大时期次数100
    每期迭代次数1000
    步长值60, 80, 100
    下载: 导出CSV

    表 2  方法AP对比

    SSD模型(算法)损失函数优化方法AP
    SSD300SGD0.561
    SSD300Adam0.674
    SSD512SGD0.736
    SSD512Adam0.815
    文献[16]算法0.761
    下载: 导出CSV
  • 加载中
图(12)表(2)
计量
  • PDF下载量:  38
  • 文章访问数:  397
  • HTML全文浏览量:  127
文章相关
  • 通讯作者:  张青华, zhangqinghuamail@163.com
  • 收稿日期:  2019-05-17
  • 录用日期:  2019-12-02
  • 网络出版日期:  2019-12-10
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

/

返回文章