Defect Detection in Transmission Line Based on Scale-Invariant Feature Pyramid Networks

doi:10.3778/j.issn.1002-8331.2010-0192

Abstract

Abstract: As the existing object detection algorithms have the problem of low detection accuracy of power components and inspection defects in complex inspection scenarios of high-voltage power, defect detection in transmission line based on scale-invariant feature pyramid networks is proposed. Firstly, by applying current baseline detection methods to the problem in this article, the RepPoints v2 networks has the highest accuracy. Secondly, as FPN structure cannot effectively extract cross-level semantic information and ignoring the scale normalization in the corner point verification process of RepPoints v2, the scale-invariant feature pyramid networks（SI-FPN） structure is proposed by combining the efficient channel attention（ECA） mechanism and the scale-equalizing pyramid convolution（SEPC）. In SI-FPN, the ECA attention module enhances the features of FPN at the channel level, and then SEPC extracts scale-invariant features from FPN and fuses cross-level pyramid features. Through training and testing on the self-built data set of six objects including insulator, shock hammer, suspension clamp, insulator self explosion, shock hammer falling off and bird’s nest, the proposed method improves 1.9 percentage points on the baseline of RepPoints v2, and the mAP reaches 96.3%. The detection accuracy is far beyond the current baseline detection models. Moreover, the SI-FPN module designed in this paper can be used as an independent structure to improve other detection models, which has certain universality.

Key words: scale-invariant feature pyramid networks（SI-FPN）, RepPoints v2, object detection, scale-equalizing pyramid convolution（SEPC）, power inspection, defects detection

摘要： 针对现有目标检测算法在高压电力复杂巡检场景下电力部件与巡检缺陷检测精度较低的问题，提出一种基于尺度不变特征金字塔的输电线路缺陷检测方法。将主流目标检测方法用于该场景，对比得出RepPoints v2网络模型的检测精度最高。针对RepPoints v2中FPN结构不能有效提取跨层次间语义信息及角点验证过程中忽略尺度归一化的问题，结合高效通道注意力模块（ECA）与尺度均衡金字塔卷积（SEPC）提出了一种尺度不变特征金字塔结构SI-FPN（scale-invariant feature pyramid networks）。其中ECA注意力模块对FPN的特征进行通道级别的增强，之后SEPC从FPN中提取尺度不变特征并对跨层次的金字塔特征进行融合。通过在自建的包含绝缘子、防震锤、悬垂线夹、绝缘子自爆、防震锤脱落与鸟巢六类对象的数据集上进行训练测试表明，该方法在RepPoints v2的基准上提升1.9个百分点，mAP达到96.3%，检测精度远超当前基准检测模型，且所设计的SI-FPN模块可作为一种独立的结构改善其他检测模型，具有一定的通用性。

关键词: 尺度不变特征金字塔结构（SI-FPN）, RepPoints v2, 目标检测, 尺度均衡金字塔卷积（SEPC）, 电力巡检, 缺陷检测

ZHAO Jielun, ZHANG Xingzhong, DONG Hongyue. Defect Detection in Transmission Line Based on Scale-Invariant Feature Pyramid Networks[J]. Computer Engineering and Applications, 2022, 58(8): 289-296.

赵杰伦, 张兴忠, 董红月. 基于尺度不变特征金字塔的输电线路缺陷检测[J]. 计算机工程与应用, 2022, 58(8): 289-296.

References

[1] NGUYEN V N，JENSSEN R，ROVERSO D.Automatic autonomous vision-based power line inspection：a review of current status and the potential role of deep learning[J].International Journal of Electrical Power & Energy Systems，2018，99：107-120.
[2] 邹栋.输电线路中关键部件图像识别及异常检测方法研究[D].北京：华北电力大学，2017.
ZOU D.Research on recognition of key components and detection of anomaly in transmission line[D].Beijing：North China Electric Power University，2017.
[3] ANTWI-BEKOE E，ZHAN Q，XIE X，et al.Insulator recognition and fault detection using deep learning approach[J].Journal of Physics Conference Series，2020，1454：012011.
[4] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[5] CHEN S，SU C，KUANG Z，et al.Real-time detection of UAV detection image of power line insulator bursting based on YOLOV3[J].Journal of Physics Conference Series，2020，1544：012117.
[6] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[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）：165-169.
ZHAO Z B，CUI Y P，QI Y C，et al.Detection method of insulator in aerial inspection image based on modified R-FCN[J].Computer Science，2019，46（3）：165-169.
[8] DAI J，LI Y，HE K，et al.R-FCN：object detection via region-based fully convolutional networks[C]//Advances in Neural Information Processing Systems，2016：379-387.
[9] HAO J，WULIN H，JING C，et al.Detection of bird nests on power line patrol using single shot detector[C]//2019 Chinese Automation Congress（CAC），2020.
[10] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[11] 王纪武，罗海保，鱼鹏飞，等.基于Faster R-CNN的多尺度高压塔鸟巢检测[J].北京交通大学学报，2019，43（5）：37-43.
WANG J W，LUO H B，YU P F，et al.Bird’s nest detection in multi-scale of high-voltage tower based on Faster R-CNN[J].Journal of Beijing Jiaotong University，2019，43（5）：37-43.
[12] 师飘，张超，郑祥明.基于深度学习的高压杆塔异物检测[J].重庆科技学院学报（自然科学版），2020，22（2）：83-87.
SHI P，ZHANG C，ZHENG X M.Foreign object detection in high-voltage towers based on deep learning[J].Journal of Chongqing University of Science and Technology（Natural Sciences Edition），2020，22（2）：83-87.
[13] LI Z，WANG W，LI T，et al.Defect diagnosis technology of typical components on transmission line based on fully convolutional network[J].Journal of Physics：Conference Series，2020，1453：012108.
[14] ZHAO G W，WANG Q，ZHANG J，et al.Lightweight neural network for component recognition and fault detection of large-scale transmission line[J].IOP Conference Series：Materials Science and Engineering，2020，768（7）：072070.
[15] CHEN Y，ZHANG Z，CAO Y，et al.RepPoints V2：verification meets regression for object detection[J].arXiv：2007.08508，2020.
[16] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.
[17] WANG X，ZHANG S，YU Z，et al.Scale-equalizing pyramid convolution for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：13359-13368.
[18] WANG Q，WU B，ZHU P，et al.ECA-net：efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：11534-11542.
[19] GIRSHICK R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision（ICCV），2016.
[20] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[21] ZHOU X，WANG D，KR?HENBüHL P.Objects as points[J].arXiv：1904.07850，2019.
[22] ZHOU X，ZHUO J，KRAHENBUHL P.Bottom-up object detection by grouping extreme and center points[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：850-859.
[23] YANG Z，LIU S，HU H，et al.Reppoints：point set representation for object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2019：9657-9666.
[24] 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.
[25] TIAN Z，SHEN C，CHEN H，et al.FCOS：fully convolutional one-stage object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2019：9627-9636.
[26] LAW H，DENG J.Cornernet：detecting objects as paired keypoints[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：734-750.
[27] ZHANG S，CHI C，YAO Y，et al.Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：9759-9768.
[28] KONG T，SUN F，LIU H，et al.FoveaBox：beyound anchor-based object detection[J].IEEE Transactions on Image Processing，2020，29：7389-7398.
[29] ZHANG X，WAN F，LIU C，et al.Freeanchor：learning to match anchors for visual object detection[C]//Advances in Neural Information Processing Systems，2019：147-155.
[30] PANG J，CHEN K，SHI J，et al.Libra R-CNN：towards balanced learning for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：821-830.
[31] ZHU C，HE Y，SAVVIDES M.Feature selective anchor-free module for single-shot object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：840-849.
[32] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision & Pattern Recognition，2016.
[33] ZHU X，HU H，LIN S，et al.Deformable convnets v2：more deformable，better results[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：9308-9316.