[1]翟永杰,杨旭,赵振兵,等.融合共现推理的Faster R-CNN输电线路金具检测[J].智能系统学报,2021,16(2):237-246.[doi:10.11992/tis.202012023]
ZHAI Yongjie,YANG Xu,ZHAO Zhenbing,et al.Integrating co-occurrence reasoning for Faster R-CNN transmission line fitting detection[J].CAAI Transactions on Intelligent Systems,2021,16(2):237-246.[doi:10.11992/tis.202012023]
点击复制
ZHAI Yongjie,YANG Xu,ZHAO Zhenbing,et al.Integrating co-occurrence reasoning for Faster R-CNN transmission line fitting detection[J].CAAI Transactions on Intelligent Systems,2021,16(2):237-246.[doi:10.11992/tis.202012023]
融合共现推理的Faster R-CNN输电线路金具检测
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第2期
页码:
237-246
栏目:
学术论文—机器学习
出版日期:
2021-03-05
- Title:
- Integrating co-occurrence reasoning for Faster R-CNN transmission line fitting detection
- Keywords:
- transmission lines; fitting; deep learning; object detection; Faster R-CNN; structured assembly; co-occurrence matrix; co-occurrence reasoning module
- 分类号:
- TP18
- 摘要:
- 为促进目标检测模型与电力领域业务知识有机融合，缓解金具样本间长尾分布问题，有效提升输电线路金具的自动化检测效果，提出了融合共现推理的Faster R-CNN(faster region-based convolutional neural network)输电线路金具检测模型。首先，深入研究输电线路金具结构化组合规则，通过数据驱动的方式以条件概率对金具目标间的共现连接关系进行有效表达；然后，结合图学习方法，利用学习并映射的共现概率关联作为共现图邻接矩阵，使用基线模型(Faster R-CNN)提取的特征向量作为图推理输入特征，以自学习的变换矩阵作为共现图传播权重，完成图信息传播并实现有效的共现推理模型嵌入。实验证明，融合共现推理模块的Faster R-CNN模型较原始模型提升了6.56%的准确率，对于长尾分布样本中数量较少的金具性能提升尤其显著。
- Abstract:
- To promote the organic integration of object detection and business knowledge in the electric power field, alleviate the problem of long-tailed distribution among fitting samples, and effectively improve the automatic detection effect of transmission line fittings, we propose a faster region-based convolutional neural network (Faster R-CNN) transmission line fitting detection model based on integrating co-occurrence reasoning. First, the structural combination rule of transmission line fittings is extensively investigated, and the co-occurrence connection relationship between objects is effectively expressed using conditional probability in a data-driven manner. Then, in combination with the graph learning method, the co-occurrence probability association is learned and mapped as the adjacency matrix of the co-occurrence graph, the feature vector extracted from the baseline model (Faster R-CNN) is used as the graph inference input feature, and the self-learning transformation matrix is used as the propagation weight of the co-occurrence graph to complete graph information propagation and realize effective co-occurrence inference model embedding. The experimental results show that the Faster R-CNN integrating co-occurrence reasoning module outperforms the original model by 6.56%, which is particularly significant for performance improvement in terms of transmission line fitting detection with a reduced long-tailed distribution among fitting samples.
- 参考文献/References:
-
[1] 方苏, 李立学, 郑益慧, 等. 基于激光测距成像和图像处理的输电线路防护技术[J]. 电气自动化, 2017, 39(3):6-8, 22
FANG Su, LI Lixue, ZHENG Yihui, et al. Protection technology for transmission lines based on laser range imaging and image processing[J]. Electrical automation, 2017, 39(3):6-8, 22
[2] 王炜, 袁奇, 顾俊杰, 等. X射线无损探伤技术在检测输电线路压接金具中的应用[J]. 上海交通大学学报, 2018, 52(10):1189-1194
WANG Wei, YUAN Qi, GU Junjie, et al. Application of X-ray nondestructive flaw detection technology in transmission line’s press fittings[J]. Journal of Shanghai JiaoTong University, 2018, 52(10):1189-1194
[3] 张秋雁, 杨忠, 姜遇红, 等. 一种基于CNN的航拍输电线路图像分类方法[J]. 应用科技, 2019, 46(6):41-45
ZHANG Qiuyan, YANG Zhong, JIANG Yuhong, et al. CNN-based aerial image classification method for aerial transmission lines[J]. Applied Science and Technology, 2019, 46(6):41-45
[4] 赵文清, 程幸福, 赵振兵, 等. 注意力机制和Faster RCNN相结合的绝缘子识别[J]. 智能系统学报, 2020, 15(1):92-98
ZHAO Wenqing, CHENG Xingfu, ZHAO Zhenbing, et al. Insulator recognition based on attention mechanism and Faster RCNN[J]. CAAI transactions on intelligent systems, 2020, 15(1):92-98
[5] DENG Chuang, WANG Shengwei, HUANG Zhi, et al. Unmanned aerial vehicles for power line inspection:a cooperative way in platforms and communications[J]. Journal of communications, 2014, 9(9):687-692.
[6] 陈晓娟, 吴英石, 赵亮. 基于随机Hough变换的OPGW防震锤识别[J]. 黑龙江电力, 2010, 32(1):1-2, 5
CHEN Xiaojuan, WU Yingshi, ZHAO Liang. Identification of OPGW vibration damper based on random Hough transformation[J]. Heilongjiang electric power, 2010, 32(1):1-2, 5
[7] 王朝硕, 李伟性, 郑武略, 等. 一种改进SSD的输电线路电力部件识别方法[J]. 应用科技, 2020, 47(4):75-81
WANG Chaoshuo, LI Weixing, ZHENG Wulue, et al. An improved SSD method for power component identification of transmission lines[J]. Applied science and technology, 2020, 47(4):75-81
[8] 王伟, 刘国海. 绝缘子图像的边缘检测[J]. 微计算机信息, 2008, 24(27):308-309, 154
WANG Wei LIU Guohai. Image edge detection of the insulator[J]. Microcomputer information, 2008, 24(27):308-309, 154
[9] 王身丽, 黄力, 侯金华, 等. 基于最大熵的复合绝缘子表面水珠图像分割算法研究[J]. 通信电源技术, 2018, 35(1):48-50
WANG Shenli, HUANG Li, HOU Jinhua, et al. Study on segmentation method of water drops image on composite insulator based on maximum entropy[J]. Telecom power technology, 2018, 35(1):48-50
[10] 王万国, 张晶晶, 韩军, 等. 基于无人机图像的输电线断股与异物缺陷检测方法[J]. 计算机应用, 2015, 35(8):2404-2408
WANG Wanguo, ZHANG Jingjing, HAN Jun, et al. Broken strand and foreign body fault detection method for power transmission line based on unmanned aerial vehicle image[J]. Journal of computer applications, 2015, 35(8):2404-2408
[11] 胡彩石, 吴功平, 曹珩, 等. 高压输电线路巡线机器人障碍物视觉检测识别研究[J]. 传感技术学报, 2008, 21(12):2092-2096
HU Caishi, WU Gongping, CAO Heng, et al. Research of obstacle recognition based on vision for high voltage transmission line inspection robot[J]. Chinese journal of sensors and actuators, 2008, 21(12):2092-2096
[12] 赵建坤, 王璋奇, 刘世钊. 基于灰度共生矩阵纹理特征的输电导线识别[J]. 云南电力技术, 2015, 43(2):126-129
ZHAO Jiankun, WANG Zhangqi, LIU Shizhao. Research on transmission line recognition based on GLCM texture feature[J]. Yunnan electric power, 2015, 43(2):126-129
[13] 金立军, 闫书佳, 刘源. 基于类Haar特征与级联AdaBoost算法的防震锤识别[J]. 系统仿真学报, 2012, 24(9):1806-1809
JIN Lijun, YAN Shujia, LIU Yuan. Vibration damper recognition based on Haar-like features and cascade AdaBoost classifier[J]. Journal of system simulation, 2012, 24(9):1806-1809
[14] 翟永杰, 王迪, 赵振兵. 基于目标建议与结构搜索的绝缘子识别方法[J]. 华北电力大学学报, 2016, 43(4):66-71, 78
ZHAI Yongjie, WANG Di, ZHAO Zhenbing. Recognition method of insulator based on object proposals and structure research[J]. Journal of North China Electric Power University, 2016, 43(4):66-71, 78
[15] 姜惠兰, 崔虎宝, 刘飞, 等. 基于模糊逻辑和支持向量机的高压输电线路故障分类器[J]. 中国电力, 2005, 38(3):13-17
JIANG Huilan, CUI Hubao, LIU Fei, et al. High voltage transmission line fault classification based on fuzzy logic and Support Vector Machines[J]. Electric power, 2005, 38(3):13-17
[16] 谢小瑜, 周俊煌, 张勇军. 深度学习在泛在电力物联网中的应用与挑战[J]. 电力自动化设备, 2020, 40(4):77-87
XIE Xiaoyu, ZHOU Junhuang, ZHANG Yongjun. Application and challenge of deep learning in Ubiquitous Power Internet of Things[J]. Electric power automation equipment, 2020, 40(4):77-87
[17] FANG Ting, JIN Xin, HU Xingliu, et al. A fast insulator-contour-detection-algorithm on power transmission lines images[J]. Applied mechanics and materials, 2012, 201-202:337-343.
[18] 杨罡, 孙昌雯, 张娜, 等. 基于多尺度特征融合的输电线路关键部件检测[J]. 电测与仪表, 2020, 57(3):54-59
YANG Gang, SUN Changwen, ZHANG Na, et al. Detection of key components of transmission lines based on multi-scale feature fusion[J]. Electrical measurement & instrumentation, 2020, 57(3):54-59
[19] 吉志朋, 张国伟, 卢秋红. 基于感受野模块的绝缘子实时识别定位方法[J]. 电工电气, 2020(9):19-22, 32
JI Zhipeng, ZHANG Guowei, LU Qiuhong. Real time detection of insulator by RFB[J]. Electrotechnics electric, 2020(9):19-22, 32
[20] 李伟性, 郑武略, 王宁, 等. 基于SSD算法的输电线路上绝缘子缺陷检测方法研究[J]. 仪器仪表用户, 2019, 26(8):1-4
LI Weixing, ZHENG Wulue, WANG Ning, et al. Research on detection method of insulator defects on transmission lines based on SSD algorithm[J]. Instrumentation customer, 2019, 26(8):1-4
[21] 赵强, 左石. 输电线路金具理论与应用[M]. 北京:中国电力出版社, 2013:2-12.
[22] 宣冬梅, 王菊韵, 于华, 等. 深度学习中先验知识的应用[J]. 计算机工程与设计, 2015, 36(11):3087-3091
XUAN Dongmei, WANG Juyun, YU Hua, et al. Application of prior knowledge in deep learning[J]. Computer engineering and design, 2015, 36(11):3087-3091
[23] 宋万潼, 李冰锋, 费树岷. 基于先验知识的航拍绝缘子检测方法研究[J]. 计算机工程, 2020
SONG Wantong, LI Bingfeng, FEI Shumin. Research on detection method of insulator in aerial image based on prior knowledge[J]. Computer engineering, 2020
[24] GALLEGUILLOS C, RABINOVICH A, BELONGIE S. Object categorization using co-occurrence, location and appearance[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA, 2008:1-8.
[25] 宋万潼, 李冰锋, 费树岷. 基于先验知识的航拍绝缘子检测方法研究[J/OL]. 计算机工程:1-11[2021-05-11].https://doi.org/10.19678/j.issn.1000-3428.0058448.
SONG Wantong, LI Bingfeng, FEI Shumin. Research on detection method of insulator in aerial image based on prior knowledge[J/OL]. Computer engineering, 2020:1-11[2021-05-11].https://doi.org/10.19678/j.issn.1000-3428.0058448.
[26] JIANG Chenhan, XU Hang, LIANG Xiaodan, et al. Hybrid knowledge routed modules for large-scale object detection[C]//Proceedings of the 32nd Conference on Neural Information Processing Systems. Montréal, Canada, 2018:1552-1563.
[27] 马巧慧. 基于伞裙形态学的绝缘子故障检测方法[J]. 科学技术创新, 2020(31):20-21
MA Qiaohui. An insulator fault detection method based on skirt morphology[J]. Scientific and technological innovation, 2020(31):20-21
[28] REN S, HE K, GIRSHICK R. Faster R-CNN:towards real-time object detection with region proposal networks[C]//Proceedings of the Advances in Neural Information Processing Systems. 2015:91-99.
[29] LIU Wei, ANGUELOV D, ERHAN D. SSD:Single shot MultiBox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016:21-37.
[30] Ren S, He K, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6):1137-1149.
[31] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014:580-587.
[32] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015:1440-1448.
[33] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 42(2):318-327.
- 相似文献/References:
-
[1]岳湘,王洪光,姜勇,等.一种110kV输电线路巡检机器人机构研究[J].智能系统学报,2016,11(2):155.[doi:10.11992/tis.201511032]
YUE Xiang,WANG Hongguang,JIANG Yong,et al.Design approach for a 110 kV power transmission line inspection robot mechanism[J].CAAI Transactions on Intelligent Systems,2016,11():155.[doi:10.11992/tis.201511032]
[2]宋屹峰,王洪光,康文杰,等.DOI面向断股补修作业任务的电力机器人机构设计[J].智能系统学报,2017,12(2):150.[doi:10.11992/tis.201605004]
SONG Yifeng,WANG Hongguang,KANG Wenjie,et al.Optimizing electric power robot design for broken-strand repair tasks[J].CAAI Transactions on Intelligent Systems,2017,12():150.[doi:10.11992/tis.201605004]
[3]赵振兵,王睿,赵文清,等.基于图知识推理的输电线路缺销螺栓识别方法[J].智能系统学报,2023,18(2):372.[doi:10.11992/tis.202205004]
ZHAO Zhenbing,WANG Rui,ZHAO Wenqing,et al.Pin-missing bolts recognition method for transmission lines based on graph knowledge reasoning[J].CAAI Transactions on Intelligent Systems,2023,18():372.[doi:10.11992/tis.202205004]
[4]戚银城,耿劭锋,赵振兵,等.基于特征迁移的螺栓图像超分辨率处理方法[J].智能系统学报,2023,18(4):858.[doi:10.11992/tis.202201009]
QI Yincheng,GENG Shaofeng,ZHAO Zhenbing,et al.A method for super resolution processing of bolt image based on feature transfer[J].CAAI Transactions on Intelligent Systems,2023,18():858.[doi:10.11992/tis.202201009]
[5]翟永杰,王乾铭,杨旭,等.融合外部知识的输电线路多金具解耦检测方法[J].智能系统学报,2022,17(5):980.[doi:10.11992/tis.202107026]
ZHAI Yongjie,WANG Qianming,YANG Xu,et al.A multi-fitting decoupling detection method for transmission lines based on external knowledge[J].CAAI Transactions on Intelligent Systems,2022,17():980.[doi:10.11992/tis.202107026]
[6]戚银城,赵席彬,耿劭锋,等.基于遮挡关系推理的输电线路图像金具检测[J].智能系统学报,2022,17(6):1154.[doi:10.11992/tis.202108036]
QI Yincheng,ZHAO Xibin,GENG Shaofeng,et al.Fittings detection in transmission line images with occlusion relation inference[J].CAAI Transactions on Intelligent Systems,2022,17():1154.[doi:10.11992/tis.202108036]
[7]王巍,杨耀权,王乾铭,等.嵌入视觉关系掩码的多类别金具检测方法[J].智能系统学报,2023,18(3):440.[doi:10.11992/tis.202202021]
WANG Wei,YANG Yaoquan,WANG Qianming,et al.A multi-category fitting detection method with embedded visual relation masks[J].CAAI Transactions on Intelligent Systems,2023,18():440.[doi:10.11992/tis.202202021]
[8]赵振兵,郭广学,王艺衡,等.融合边缘感知与统计纹理知识的输电线路金具锈蚀检测[J].智能系统学报,2024,19(5):1228.[doi:10.11992/tis.202306009]
ZHAO Zhenbing,GUO Guangxue,WANG Yiheng,et al.Rust detection in transmission line fittings via fusion of edge perception and statistical texture knowledge[J].CAAI Transactions on Intelligent Systems,2024,19():1228.[doi:10.11992/tis.202306009]
备注/Memo
收稿日期:2020-12-15。
基金项目:国家自然科学基金项目（61871182、61773160）；北京市自然科学基金项目（4192055）；河北省自然科学基金项目（F2020502009）
作者简介:翟永杰，教授，博士，主要研究方向为电力视觉。主持国家自然科学基金面上项目1项，河北省自然科学基金项目1项，主持横向科研项目多项，参与国家重点研发计划项目1项，获山东省科技进步一等奖1项。发表论文30余篇，授权发明专利10项，编著1部，参编教材1部、著作3部;杨旭，硕士研究生，主要研究方向为电力视觉与人工智能;赵振兵，教授，博士，主要研究方向为电力视觉。主持国家自然科学基金等纵向课题10项；获省科技进步一等奖1项(第3完成人)；以第1完成人获得国家专利授权16项；以第1作者出版专著2部，发表学术论文30余篇
通讯作者:赵振兵.E-mail:zhaozhenbing@ncepu.edu.cn
更新日期/Last Update:
2021-04-25