Guishen Tian, Song Meng, Xuejiao Bai, Lijuan Liu, Y. Zhi, Binbin Zhao, Luo Meng
{"title":"基于卫星遥感和深度学习的输电线路建设进度监测与辅助审计策略研究","authors":"Guishen Tian, Song Meng, Xuejiao Bai, Lijuan Liu, Y. Zhi, Binbin Zhao, Luo Meng","doi":"10.1109/ITCA52113.2020.00023","DOIUrl":null,"url":null,"abstract":"The monitoring and auditing of the construction progress of the transmission line is of great significance to the construction management and smooth acceptance of the project. Its key focus includes the number of completed transmission towers and the estimation of related consumables. Therefore, focusing on transmission tower detection and wire consumables estimation, this paper preliminarily explores and establishes the technical framework of transmission line construction progress monitoring and auxiliary audit based on satellite remote sensing and deep learning. This paper proposes an improved DRBox (Detector with Rotatable Boxes) model and satellite remote sensing wire consumables estimation model based on high-resolution optical satellite remote sensing image, which are applied in a transmission line section of Mengdong Company. Experiments show that the automatic detection accuracy of transmission towers in this paper is higher than 93.52%, and the average estimation accuracy of wire consumables is about 97.3%. At the same time, it can quickly count the number of transmission line towers built at different times, which improves the monitoring of transmission line construction progress and enhances the efficiency, objectivity and intelligence level of wire consumables audit.","PeriodicalId":103309,"journal":{"name":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","volume":"11 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Research on Monitoring and Auxiliary Audit Strategy of Transmission Line Construction Progress Based on Satellite Remote Sensing and Deep Learning\",\"authors\":\"Guishen Tian, Song Meng, Xuejiao Bai, Lijuan Liu, Y. Zhi, Binbin Zhao, Luo Meng\",\"doi\":\"10.1109/ITCA52113.2020.00023\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The monitoring and auditing of the construction progress of the transmission line is of great significance to the construction management and smooth acceptance of the project. Its key focus includes the number of completed transmission towers and the estimation of related consumables. Therefore, focusing on transmission tower detection and wire consumables estimation, this paper preliminarily explores and establishes the technical framework of transmission line construction progress monitoring and auxiliary audit based on satellite remote sensing and deep learning. This paper proposes an improved DRBox (Detector with Rotatable Boxes) model and satellite remote sensing wire consumables estimation model based on high-resolution optical satellite remote sensing image, which are applied in a transmission line section of Mengdong Company. Experiments show that the automatic detection accuracy of transmission towers in this paper is higher than 93.52%, and the average estimation accuracy of wire consumables is about 97.3%. At the same time, it can quickly count the number of transmission line towers built at different times, which improves the monitoring of transmission line construction progress and enhances the efficiency, objectivity and intelligence level of wire consumables audit.\",\"PeriodicalId\":103309,\"journal\":{\"name\":\"2020 2nd International Conference on Information Technology and Computer Application (ITCA)\",\"volume\":\"11 1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 2nd International Conference on Information Technology and Computer Application (ITCA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITCA52113.2020.00023\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 2nd International Conference on Information Technology and Computer Application (ITCA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITCA52113.2020.00023","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
输变电线路施工进度的监测与审计对工程的施工管理和顺利验收具有重要意义。其重点包括完成的输电塔数量和相关消耗品的估计。因此,本文围绕输电塔检测和电线耗材估算,初步探索并建立了基于卫星遥感和深度学习的输电线路建设进度监测与辅助审计的技术框架。本文提出了基于高分辨率光学卫星遥感影像的改进DRBox (Detector with Rotatable Boxes)模型和卫星遥感线材估算模型,并应用于孟东公司某输电线路段。实验表明,本文对输电塔的自动检测精度高于93.52%,对线材耗材的平均估计精度约为97.3%。同时,可以快速统计不同时间建设的输电线路塔的数量,提高了对输电线路建设进度的监控,提高了电线耗材审计的效率、客观性和智能化水平。
Research on Monitoring and Auxiliary Audit Strategy of Transmission Line Construction Progress Based on Satellite Remote Sensing and Deep Learning
The monitoring and auditing of the construction progress of the transmission line is of great significance to the construction management and smooth acceptance of the project. Its key focus includes the number of completed transmission towers and the estimation of related consumables. Therefore, focusing on transmission tower detection and wire consumables estimation, this paper preliminarily explores and establishes the technical framework of transmission line construction progress monitoring and auxiliary audit based on satellite remote sensing and deep learning. This paper proposes an improved DRBox (Detector with Rotatable Boxes) model and satellite remote sensing wire consumables estimation model based on high-resolution optical satellite remote sensing image, which are applied in a transmission line section of Mengdong Company. Experiments show that the automatic detection accuracy of transmission towers in this paper is higher than 93.52%, and the average estimation accuracy of wire consumables is about 97.3%. At the same time, it can quickly count the number of transmission line towers built at different times, which improves the monitoring of transmission line construction progress and enhances the efficiency, objectivity and intelligence level of wire consumables audit.