[1]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.[doi:10.11992/tis.201907023]
 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.[doi:10.11992/tis.201907023]
点击复制

注意力机制和Faster RCNN相结合的绝缘子识别(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年1期
页码:
92-98
栏目:
学术论文—机器感知与模式识别
出版日期:
2020-01-01

文章信息/Info

Title:
Insulator recognition based on attention mechanism and Faster RCNN
作者:
赵文清1 程幸福1 赵振兵2 翟永杰1
1. 华北电力大学 控制与计算机工程学院, 河北 保定 071003;
2. 华北电力大学 电气与电子工程学院, 河北 保定 071003
Author(s):
ZHAO Wenqing1 CHENG Xingfu1 ZHAO Zhenbing2 ZHAI Yongjie1
1. School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China;
2. School of Electrical and Electronic Engineering, North China Electric Power University, Baoding 071003, China
关键词:
Faster RCNN绝缘子注意力机制SENet特征通道RPN建议框特征向量
Keywords:
Faster RCNNinsulatorattention mechanismSENetcharacteristic channelRPNproposal boxesfeature vector
分类号:
TP391
DOI:
10.11992/tis.201907023
摘要:
针对利用Faster RCNN识别绝缘子图像过程中定位不够准确的问题,提出一种注意力机制和Faster RCNN相结合的绝缘子识别方法。在特征提取阶段引入基于注意力机制的挤压与激励网络(Squeeze-and-Excitation Networks,SENet)结构,使模型能够关注与目标相关的特征通道并弱化其他无关的特征通道;根据绝缘子的特点,对区域建议网络(region proposal network,RPN)生成锚点(anchor)的比例和尺度进行调整;在全连接层运用注意力机制对周围建议框的特征向量赋予不同权重并进行融合,更新目标建议框的特征向量。实验结果表明:与传统的Faster RCNN算法相比,改进后的算法能够较好地识别出绝缘子。
Abstract:
In order to solve the problem of inaccurate location in the process of recognizing insulator image using Faster RCNN, this paper proposes an insulator recognition method based on attention mechanism and Faster RCNN. Firstly, the Squeeze-and-Excitation Networks (SENet) structure based on attention mechanism is introduced in the feature extraction stage to enable the model to focus on the target-related feature channels and weaken other irrelevant feature channels. Then, according to the characteristics of insulators, the proportion and scale of anchors generated by regional proposal network (RPN) are adjusted. Finally, the attention mechanism is applied in the full connected layer to give different weights to the feature vectors of the surrounding suggestion boxes and fuse them to update the feature vectors of the target suggestion boxes. The experimental results show that the improved algorithm can recognize insulators better than the traditional Faster RCNN algorithm.

参考文献/References:

[1] 张倩, 王建平, 李帷韬. 基于反馈机制的卷积神经网络绝缘子状态检测方法[J]. 电工技术学报, 2019, 34(16): 3311–3321
ZHANG Qian, WANG Jianping, LI Weitao. Insulator state detection of convolutional neural networks based on feedback mechanism[J]. Transactions of China electrotechnical society, 2019, 34(16): 3311–3321
[2] 刘召, 张黎明, 耿美晓, 等. 基于改进的Faster R-CNN高压线缆目标检测方法[J]. 智能系统学报, 2019, 14(4): 627–634
LIU Zhao, ZHANG Liming, GENG Meixiao, et al. Object detection of high-voltage cable based on improved Faster R-CNN[J]. CAAI transactions on intelligent systems, 2019, 14(4): 627–634
[3] 黄宵宁, 张真良. 直升机巡检航拍图像中绝缘子图像的提取算法[J]. 电网技术, 2010, 34(1): 194–197
HUANG Xiaoning, ZHANG Zhenliang. A method to extract insulator image from aerial image of helicopter patrol[J]. Power system technology, 2010, 34(1): 194–197
[4] IRUANSI U, TAPAMO J R, DAVIDSON I E. An active contour approach to insulator segmentation[C]//AFRICON 2015. Addis Ababa, Ethiopia, 2015: 1–5.
[5] 左国玉, 马蕾, 徐长福, 等. 基于跨连接卷积神经网络的绝缘子检测方法[J]. 电力系统自动化, 2019, 43(4): 101–108
ZUO Guoyu, MA Lei, XU Changfu, et al. Insulator detection method based on cross-connected convolutional neural network[J]. Automation of electric power systems, 2019, 43(4): 101–108
[6] 彭向阳, 刘洋, 王柯, 等. 利用卷积神经网络进行绝缘子自动定位[J]. 武汉大学学报(信息科学版), 2019, 44(4): 563–569
PENG Xiangyang, LIU Yang, WANG Ke, et al. An automatically locating method for insulator object based on CNNs[J]. Geomatics and Information Science of Wuhan University, 2019, 44(4): 563–569
[7] 赵振兵, 崔雅萍, 戚银城, 等. 基于改进的R-FCN航拍巡线图像中的绝缘子检测方法[J]. 计算机科学, 2019, 46(3): 159–163
ZHAO Zhenbing, CUI Yaping, QI Yincheng, et al. Detection method of insulator in aerial inspection image based on modified R-FCN[J]. Computer science, 2019, 46(3): 159–163
[8] 程海燕, 翟永杰, 陈瑞. 基于Faster R-CNN的航拍图像中绝缘子识别[J]. 现代电子技术, 2019, 42(2): 98–102
CHENG Haiyan, ZHAI Yongjie, CHEN Rui. Faster R-CNN based recognition of insulators in aerial images[J]. Modern electronics technique, 2019, 42(2): 98–102
[9] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 7132–7141.
[10] 徐诚极, 王晓峰, 杨亚东. Attention-YOLO: 引入注意力机制的YOLO检测算法[J]. 计算机工程与应用, 2019, 55(6): 13–23
XU Chengji, WANG Xiaofeng, YANG Yadong. Attention-YOLO: YOLO detection algorithm that introduces attention mechanism[J]. Computer engineering and applications, 2019, 55(6): 13–23
[11] 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
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
[12] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International journal of computer vision, 2014, 115(3):211–252.
[13] 林刚, 王波, 彭辉, 等. 基于改进Faster-RCNN的输电线巡检图像多目标检测及定位[J]. 电力自动化设备, 2019, 39(5): 213–218
LIN Gang, WANG Bo, PENG Hui, et al. Multi-target detection and location of transmission line inspection image based on improved Faster-RCNN[J]. Electric power automation equipment, 2019, 39(5): 213–218
[14] REN Shaoqing, HE Kaiming, 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, 2017, 39(6): 1137–1149.
[15] YANG Jianwei, LU Jiasen, LEE S, et al. Graph R-CNN for scene graph generation[C]//Proceedings of 15th European Conference on Computer Vision. Munich, Germany, 2018: 670–685.
[16] TAO Xian, ZHANG Dapeng, WANG Zihao, et al. Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J]. IEEE transactions on systems, man, and cybernetics: systems, 2020, 50(4): 1486–1498.

备注/Memo

备注/Memo:
收稿日期:2019-07-15。
基金项目:国家自然科学基金项目(61871182,61773160)
作者简介:赵文清,教授,博士,主要研究方向为人工智能与数据挖掘。发表学术论文50余篇;程幸福,硕士研究生,主要研究方向为机器学习、深度学习、目标检测;赵振兵,副教授,博士,主要研究方向为深度学习、计算机视觉
通讯作者:赵文清.E-mail:jbzwq@126.com
更新日期/Last Update: 1900-01-01