基于卫星影像的输电线路周边地表隐患识别方法

doi:10.7523/j.ucas.2022.018

摘要/Abstract

摘要： 我国输电线路面临着多种周边地物影响带来的安全隐患，线路隐患排查对确保国家电力可靠供应及电力安全具有重要意义。当前各种线路隐患排查方法面临不同的困难，而卫星遥感技术可提供低成本、非接触的快速解决方案。探索使用卫星遥感影像实现输电线路周边地表隐患识别与提取的解决方案，提出一种针对输电线路周边地表隐患识别提取的方法，使用多类别残差修正模块进行结果修正，减少小尺度目标识别不佳及类别边缘误判的情况，使输电线路周边地表隐患识别效果得到提升。

关键词: 输电线路安全, 隐患识别, U-net, RRM_Mc

Abstract: Power transmission lines in China are faced with safety hazards brought about by a variety of surrounding features, and line hazard investigation is of great significance to ensure reliable national power supply and power security. At present, various methods of line hidden danger investigation face different difficulties, and satellite remote sensing technology can provide a low-cost, non-contact and rapid solution. In this paper, we use satellite remote sensing technology to realize the identification and extraction of hidden dangers on the ground along transmission lines. A method is also proposed for the identification and extraction of hidden hazards along transmission lines, using multi-category residual refinement module for result correction, which reduces the cases of poor recognition of small-scale targets and category edge misclassification, and lays the methodological foundation for the practical application of satellite remote sensing technology to the investigation of hidden dangers along power transmission lines.

Key words: transmission line safety, extraction of potential surface danger, U-net, RRM_Mc

中图分类号:

TP751

邹绍悦, 刘朔, 夏昊. 基于卫星影像的输电线路周边地表隐患识别方法[J]. 中国科学院大学学报, 2023, 40(6): 778-787.

ZOU Shaoyue, LIU Shuo, XIA Hao. Satellite image-based method for extracting potential surface dangers along power transmission lines[J]. Journal of University of Chinese Academy of Sciences, 2023, 40(6): 778-787.

参考文献

[1] 高嵩, 刘洋, 路永玲, 等. 交流特高压输电线路运行维护现状综述[J]. 江苏电机工程, 2014, 33(2):81-84.DOI:10.19464/j.cnki.cn32-1541/tm.2014.02.023.
[2] 彭向阳, 钱金菊, 麦晓明, 等. 大型无人直升机电力线路全自动巡检技术及应用[J]. 南方电网技术, 2016, 10(2):24-31, 76. DOI:10.13648/j.cnki.issn1674-0629.2016.02.004.
[3] 汤明文, 戴礼豪, 林朝辉, 等. 无人机在电力线路巡视中的应用[J]. 中国电力, 2013, 46(3):35-38.DOI:10.3969/j.issn.1004-9649.2013.03.008.
[4] 戴栋, 张敏, 赵东生, 等. 输电线路在线监测装置研制及其通信组网应用[J]. 高电压技术, 2015, 41(12):3902-3908. DOI:10.13336/j.1003-6520.hve.2015.12.004.
[5] 彭向阳, 钱金菊, 吴功平, 等. 架空输电线路机器人全自主巡检系统及示范应用[J]. 高电压技术, 2017, 43(8):2582-2591. DOI:10.13336/j.1003-6520.hve.20170731019.
[6] 张校志. 基于卫星遥感的输电走廊地表覆盖变化检测与山火易发性评估[D]. 武汉:武汉大学, 2017.
[7] 王彤, 朱凌, 范亚洲, 等. 基于改进U-net语义分割遥感影像的线路走廊隐患检测方法[J]. 南方电网技术, 2019, 13(8):67-73. DOI:10.13648/j.cnki.issn1674-0629.2019.08.010.
[8] 王彤, 范亚洲, 黄勇, 等. 基于多源高分辨率遥感影像的电网输电线路杆塔及走廊隐患检测方法研究[C]//第六届高分辨率对地观测学术年会, 2019年9月20-22日,成都.高分辨率对地观测学术联盟, 2019:191-209.
[9] 穆超. 基于多种遥感数据的电力线走廊特征物提取方法研究[D]. 武汉:武汉大学, 2010.
[10] Matikainen L, Lehtomäki M, Ahokas E, et al. Remote sensing methods for power line corridor surveys[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 119:10-31. DOI:10.1016/j.isprsjprs.2016.04.011.
[11] Melzer T, Briese C. Extraction and modeling of power lines from ALS point clouds[C]//Proceedings of 28th Workshop. Hagenberg, Austria. 2004:47-54.
[12] McLaughlin R A. Extracting transmission lines from airborne LIDAR data[J]. IEEE Geoscience and Remote Sensing Letters, 2006, 3(2):222-226. DOI:10.1109/LGRS.2005.863390.
[13] Zhang Y, Yuan X X, Li W Z, et al. Automatic power line inspection using UAV images[J]. Remote Sensing, 2017, 9(8):824. DOI:10.3390/rs9080824.
[14] 张苏, 齐立忠, 韩文军, 等. 基于无人机激光点云的树障检测与砍伐树木数量估算[J]. 中国科学院大学学报, 2020, 37(6):760-766. DOI:10.7523/j.issn.2095-6134.2020.06.006.
[15] Chen C, Yang B S, Song S, et al. Automatic clearance anomaly detection for transmission line corridors utilizing UAV-borne LIDAR data[J]. Remote Sensing, 2018, 10(4):613. DOI:10.3390/rs10040613.
[16] 丁薇, 黄绪勇, 谭向宇, 等. 基于机载激光点云的输电线路走廊树障自动化检测方法[J]. 测绘与空间地理信息, 2018, 41(11):125-128. DOI:10.3969/j.issn.1672-5867.2018.11.036.
[17] 宋爽. 基于机载LiDAR点云的电力走廊三维要素提取技术[D]. 武汉:武汉大学, 2017.
[18] Kobayashi Y, Karady G G, Heydt G T, et al. The utilization of satellite images to identify trees endangering transmission lines[J]. IEEE Transactions on Power Delivery, 2009, 24(3):1703-1709. DOI:10.1109/TPWRD.2009.2022664.
[19] Ahmad J, Malik A S, Xia L K. Vegetation monitoring for high-voltage transmission line corridors using satellite stereo images[C]//2011 National Postgraduate Conference. September 19-20, 2011, Perak, Malaysia. IEEE, 2011:1-5. DOI:10.1109/NatPC.2011.6136337.
[20] 彭文邦. 基于多光谱图像的输电线路山火检测研究[D]. 北京:华北电力大学, 2017.
[21] 丁健配. 基于图像差异的输电线路周边隐患检测系统[D]. 济南:济南大学, 2017.
[22] 焦波. 基于深度学习的输电线路目标检测与覆冰厚度识别方法研究[D]. 呼和浩特:内蒙古工业大学, 2021.
[23] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324. DOI:10.1109/5.726791.
[24] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. June 7-12, 2015, Boston, MA, USA. IEEE, 2015:3431-3440. DOI:10.1109/CVPR.2015.7298965.
[25] Badrinarayanan V, Kendall A, Cipolla R. SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495. DOI:10.1109/TPAMI.2016.2644615.
[26] Chen L C, Papandreou G, Kokkinos I, et al. DeepLab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848. DOI:10.1109/TPAMI.2017. 2699184.
[27] Ronneberger O, Fischer P, Brox T. U-net:convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, 2015:234-241.DOI:10.1007/978-3-319-24574-4_28.
[28] Shao Z F, Tang P H, Wang Z Y, et al. BRRNet:a fully convolutional neural network for automatic building extraction from high-resolution remote sensing images[J]. Remote Sensing, 2020, 12(6):1050. DOI:10.3390/rs12061050.
[29] Chen L C, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL].arXiv:1706.05587. (2017-12-05)[2022-03-01] https://ui.adsabs.harvard.edu/abs/2017arXiv170605587C.
[30] Tong X Y, Xia G S, Lu Q K, et al. Land-cover classification with high-resolution remote sensing images using transferable deep models[J]. Remote Sensing of Environment, 2020, 237:111322. DOI:10.1016/j.rse.2019.111322.