计算机科学 ›› 2022, Vol. 49 ›› Issue (5): 84-91.doi: 10.11896/jsjkx.210400142

• 计算机图形学&多媒体* 上一篇    下一篇


李发光, 伊力哈木·亚尔买买提   

  1. 新疆大学电气工程学院 乌鲁木齐830047
  • 收稿日期:2021-04-15 修回日期:2021-09-05 出版日期:2022-05-15 发布日期:2022-05-06
  • 通讯作者: 伊力哈木·亚尔买买提(65891080@qq.com)
  • 作者简介:(2434740150@qq.com)
  • 基金资助:

Real-time Detection Model of Insulator Defect Based on Improved CenterNet

LI Fa-guang, YILIHAMU·Yaermaimaiti   

  1. College of Electrical Engineering,Xinjiang University,Urumqi 830047,China
  • Received:2021-04-15 Revised:2021-09-05 Online:2022-05-15 Published:2022-05-06
  • About author:LI Fa-guang,born in 1996,postgra-duate.His main research interests include deep learning and electric power inspection.
    YILIHAMU·Yaermaimaiti,born in 1978,master,associate professor,master supervisor.His main research interests include pattern recognition and artifical intelligence.
  • Supported by:
    National Natural Science Foundation of China(61866037,61462082).

摘要: 针对无人机在电力巡检过程中对绝缘子及其缺陷检测的准确率较低、实时性较差的问题,提出一种改进CenterNet的绝缘子缺陷检测模型。首先,使用轻量级网络EfficientNet-B0代替原始模型的特征提取网络ResNet18,在保证模型提取能力的同时加快了其推理速度;其次,搭建特征加强模块(Feature Enhancement Module,FEM),并对经过上采样后的特征通道权重进行合理分配,抑制无效特征,并借鉴FPN(Feature Pyramid Networks)融合浅层与深层特征,使特征层信息更加丰富;然后在CenterNet-Head中引入空间和通道混合的注意力机制CA(Coordinate Attention),使类别和位置信息的预测更加准确;最后,使用Soft-NMS解决在模型检测过程中由中心点预测不准导致的“单目标多框”问题。实验结果表明,改进的CenterNet比原始模型的精度提高了11.92%,速度提高了8.95 FPS,模型大小减小了54 MB。与其他检测模型相比,改进模型的精度与速度均有提高,证明了其实时性和鲁棒性。

关键词: CenterNet, 绝缘子, 缺陷检测, 特征融合, 注意力机制

Abstract: Aiming at the problem that it is difficult to detect insulators and their defects in real time and efficiently in the course of electric patrol inspection of UAV,an improved insulator defect detection model based on CenterNet is proposed.Firstly,lightweight network EfficientNet-B0 is used to replace the original model’s feature extraction network ResNet18,which ensures the model extraction ability and speeds up its reasoning speed.Then,a feature enhancement module FEM is built,which distributes the weight of the feature channels after upsampling reasonably and suppresses invalid features.Using FPN (feature pyramid networks) for reference,the shallow and deep features are integrated to enrich the information of feature layer.Secondly,the coordination attention(CA) mechanism,which is a mixture of space and channel,is introduced into CenterNet-Head,which makes the prediction of category and location information more accurate.Finally,Soft-NMSis used to solve the problem of “single target and multiple frames” caused by inaccurate prediction of center points in the process of model detection.Experimental results show that the precision of the improved CenterNet is improved by 11.92%,the speed is increased by 8.95 FPS,and the model size is reduced by 54 MB.Compared with other detection models,the accuracy and speed are improved,which proves the real-time performance and robustness of the improved model.

Key words: Attention mechanism, CenterNet, Defect detection, Feature fusion, Insulator


  • TM933
[1]LING S,NGUYEN K,ROUX L A,et al.A lattic E based group signature scheme with verifier-local revocation[J].Theoretical Computer Science,2018,730(19):1-20.
[2]ZHANG M J,LI H W,ZAHO W H,et al.Applic ation of deep learning in unmanned aerial vehicle patrl inspection of military optical cable line[J].Optical Communication Research,2018(6):57-61.
[3]YANG G,SUN C W,WANG D W,et al.A Comparative Study of Transmission Line Component Detection Models Based on UAV Front-end SSD Algorithm[J].Journal of Taiyuan University of Technology,2020,51(2):212-219.
[4]REN S Q,HE K M,GIRSHICK R,et al.Faster rcnn:Towards real-time obiect dection with region proposal networks[C]//Advances in Neural Information Processing Systems.Montreal:MIT press,2015:91-99.
[5]DAI J,LI Y,HE K M,et al.R-FCN:Objectdetection via regionbased fully convolutional neworks[C]//Advancesin Neural Information Processing System.2016:379-387.
[6]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2014:580-587.
[7]GIRSHICK R.Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision.Piscataway:IEEE,2015:1440-1448.
[8]LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shotmultibox detector[C]//Proceedings of the 14th European Conference on Computer Vision(ECCV).Amsterdam,Netherlands:Springer,2016:21-37.
[9]FU C Y,LIU W,RANGA A,et al.DSSD:Deconvolutional single shot detector[J].arXiv:1701.06659,2017.
[10]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.
[11]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Computer Vision and Pattern Recognltion.IEEE,2016:779-788.
[12]REDMON J,FARHADI A,GIRSHICK R.YOLO900:faster,stronger[C]//Computer Vision and Pattern Recognition.IEEE,2017:6517-6525.
[13]REDMON J,FARHADI A.Yolov3:An incremental improve-ment[OL].[2019-06-03].https://arXiv.org/abs/1804.02767.
[14]LAW H,DENG J.Cornernet:Detecting obiect as paired key-points[C]//Proceedings of the 15th Europe an Conference on Computer Vision.Munich,Germany,2018:734-750.
[15]LAW H,TENG Y,RUSSAKOVSKY O,et al.CornerNet-Lite:Efficient keypoint based object[J].arXiv:1904.08900,2019.
[16]TIAN Z,SHEN C H,CHEN H,et al.FCOS:Fully Convolu-tional one-stage object detection[J].arXiv:1904.01355,2019.
[17]ZHAO R,ZHAO G W,ZHANG J,et al.Real-time fault detection method for high voltage transmission line based on improved algorithm[J].Computer Engineering and Applications,2021,57(17):7.
[18]YI J Y,CHEN C F,GONG G Q.Aerial Insulator Detection of Transmission Line Based on Improved Faster RCNN[J].Computer Engineering,2021,47(6):292-298,304.
[19]DUAN K W,BAI S,XIE L X,et al.CenterNet:Keypoint triplets for object detection[J].arXiv:1904.08189,2019.
[20]AN M,LE Q V.EfficientNet:Rethinking Model Scaling forConvolutional Neural Networks[C]//International Conference on Machine Learning.Long Beach,USA:ICML,2019:6105-6114.
[21]LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.2017.
[22]HOU Q B,ZHOU D Q,FENG J S.Corinate Attention for Efficient Mobile Network Design[C]//Proceedings of the 2021 IEEE Conference on Compvision and Patten Recognition.2021.
[23]BODLA N,SINGH B,CHELLAPPA R,et al.Soft-nms improving object detection with one line of code[C]//ICCV.Venice,USA:IEEE Press,2017:5562-5570.
[24]NEUBECK A,VAN G L.Efficient non-maximum suppression[C]//Proceedings of 18th International Conference on Pattern Recognition.2006:850-855.
[25]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//CVPR.Las Vegas,USA:IEEE Press,2016:770-778.
[26]ZHANG T,TAO D,YANG J,et al.Discriminative LocalityAlignment[C]//European Conference on Computer Vision.2008:725-738.
[27]NEWELL A,YANG K Y,DENG J.Stacked hourglass networks for human pose estimation[C]//Proceedings of the 14th European Conference on Computer Vision.Amsterdam,the Netherlands,2016:483-499.
[28]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense bject detection[C]//Proceedings of the 2017 IEEE Interna-tional Conference on Computer Vision.Piscataway:IEEE,2017:2980-2988.
[29]MARK S,ANDREW H,MENGLONG Z,et al.MobileNet v2:Inverted residuals and linear bottlencks[C]//CVPR.Salt Lake City,USA:IEEE Press,2018:4510-4520.
[30]JIE H,LI S,GANG S.Squeeze-and-excitation networks[C]//CVPR.Salt Lake City,USA:IEEE Press,2018:7132-7141.
[31]ZHAO Q,SHENG T,WANG Y,et al.M2det:A single-shot object detector based on multi-level feature pyramid network[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:9259-9266.
[32]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//Proceeding of the IEEE International Conference on Computer Vision.2017:2980-2988.
[33]TAN M,PANG R,LE Q,et al.EfficientDet:Scalable and efficient object detection[J].arXiv:1911.09070,2020.
[34]WANG C Y,LIAO H Y.YOLOv4:Optional speed and accuracy of objection dection[OL].[2020-04-23].https://arxiv.org/abs/2004.10934.
[1] 周芳泉, 成卫青.
Sequence Recommendation Based on Global Enhanced Graph Neural Network
计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2] 戴禹, 许林峰.
Cross-image Text Reading Method Based on Text Line Matching
计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[3] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4] 熊丽琴, 曹雷, 赖俊, 陈希亮.
Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization
计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[5] 饶志双, 贾真, 张凡, 李天瑞.
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[6] 汪鸣, 彭舰, 黄飞虎.
Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction
计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[7] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[8] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[9] 孙奇, 吉根林, 张杰.
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[10] 闫佳丹, 贾彩燕.
Text Classification Method Based on Information Fusion of Dual-graph Neural Network
计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[11] 张颖涛, 张杰, 张睿, 张文强.
Photorealistic Style Transfer Guided by Global Information
计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[12] 曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨.
Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism
计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224
[13] 程成, 降爱莲.
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[14] 徐鸣珂, 张帆.
Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
[15] 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强.
Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism
计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198
Full text



No Suggested Reading articles found!