计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 135-140.doi: 10.11896/jsjkx.230600109
郝然, 王红军, 李天瑞
HAO Ran, WANG Hongjun, LI Tianrui
摘要: 检测输电线路缺陷并及时维修可以确保电网的安全稳定,具有重大的实际意义。但输电线路图像背景复杂、元件尺寸小,导致现有的目标检测模型不能取得很好的效果,因此文中提出了基于双分支串行混合注意力的输电线路缺陷检测深度神经网络模型。该模型设计了DBSA(Dual-branch Serial Attention)双分支串行混合注意力,从而将更多的权重放在缺陷上,并提出了WCFPN(Well-connected Feature Pyramid Network)特征金字塔,让经DBSA提取的特征充分融合,从而增强模型检测小目标的能力。DBSA将特征图沿高度和宽度两个分支压缩并用一维卷积提取注意力,WCFPN设计了一种包含跨尺度融合和跳层连接的新型融合路径,让经DBSA提取的高层语义信息和低层空间信息进行更充分的交互。最后在绝缘子自爆、防振锤损坏、鸟巢异物、水泥杆破损和输电线路缺陷5个数据集上进行实验,结果显示所提模型取得了最佳的检测效果,在5个数据集上的平均AP50和AP分别为84.3%和46.1%,相比目前最先进的模型YOLOv7分别提升了3.7%和3%。
中图分类号:
[1]ZHAO Z,QI H,QI Y,et al.Detection method based on auto-matic visual shape clustering for pin-missing defect in transmission lines[J].IEEE Transactions on Instrumentation and Mea-surement,2020,69(9):6080-6091. [2]ZHANG X,ZHANG Y,LIU J,et al.InsuDet:A fault detection method for insulators of overhead transmission lines using con-volutional neural networks[J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-12. [3]LV F C,NIU L L,WANG S H,et al.Intelligent detection and parameter adjustment strategy of major electrical equipment based on optimized YOLOv4[J].Transactions of China Electrotechnical Society,2021,36(22):4837-4848. [4]LIU M,LI Z,LI Y,et al.A fast and accurate method of power line intelligent inspection based on edge computing[J].IEEE Transactions on Instrumentation and Measurement,2022,71:1-12. [5]LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single Shot Multibox Detector[C]//Computer Vision--ECCV 2016:14th European Conference.Springer International Publishing,2016:21-37. [6]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:779-788. [7]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.Yolov4:Optimal speed and accuracy of object detection[J].arXiv:2004.10934,2020. [8]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,2017,39(6):1137-1149. [9]HE K,GKIOXARI G,DOLLÁR P,et al.Mask r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2961-2969. [10]GLENN J.YOLOv5 release v6.1.[OL]https://github.com/ultralytics/yolov5/releases/tag/v6.1,2022.2,7,10. [11]WANG C Y,BOCHKOVSKIY A,LIAO H Y M.YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J].arXiv:2207.02696,2022. [12]NIU Z,ZHONG G,YU H.A review on the attention mechanism of deep learning[J].Neurocomputing,2021,452:48-62. [13]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141. [14]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19. [15]WANG Q,WU B,ZHU P,et al.ECA-Net:Efficient channel attention for deep convolutional neural networks[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11534-11542. [16]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125. [17]LIU S,QI L,QIN H,et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8759-8768. [18]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 Thirty-Third AAAI Conference on Artificial Intelligence.2019:9259-9266. [19]LU X,LI B Y,YUE Y X,et al.Grid R-CNN plus:faster and better [J].arXiv:1906.05688,2019. [20]CAI Z,VASCONCELOS N.Cascade r-cnn:Delving into highquality object detection[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2018:6154-6162. [21]CHEN Z,YANG C,LI Q,et al.Disentangle your dense object detector[C]//Proceedings of the 29th ACM International Conference on Multimedia.2021:4939-4948. |
|