输电线路巡检中的电力线追踪算法研究与工程应用
|
摘要
随着我国经济的高速发展,对电力输电网等电力基础设施的安全运行提出了更高的要求。电力线巡检是一项非常重要而繁重的工作。目前依靠人工巡检的管理与维护方式已经不能完全满足电力事业的发展要求,给电力网络的安全、管理与维护带来了极大的困难。利用航空遥感技术对电力线进行巡检已成为电力部门的迫切需求。
本文基于山东电力集团公司电力科学研究院无人直升机巡检系统项目的研究和工程应用,开发了一套检测系统,并提出了一种在复杂自然背景条件下,从无人直升机上拍摄的航空影像中实时检测高压输电线路的算法,实现了实时视频输电线路跟踪。该算法首先归纳和分析电力线在无人直升机航拍影像上的成像特征,通过改进的边缘检测算子与PCNN检测算法对电力线像素进行检测和效果比较,设计适合电力线像素检测的算子；然后利用基于先验知识的改进Hough变换算法检测直线段,再根据高压输电线路的特性,去除一些杂线,确定高压输电线路；最后,利用Kalman滤波对视频图像中的高压输电线路进行实时检测跟踪。
通过工程应用表明,该方法能有效地自动提取复杂自然背景下的高压输电线路,并能达到实时检测输电线路目的。
The rapid development of our national economy brings up higher requirement to the safe operation of infrastructures such as power transmission network. High-voltage power line inspection is very important and onerous job. Current method of manual-style inspection can not fully meet the requirement of the power industry development, and it brings great difficulties to the security, management and maintenance of power network. The inspection of power lines with remote sensing technology is the urgent needs of the electricity sector.
This paper based on research and engineering applications of unmanned helicopter inspection system of the Electric Power Research Institute of Shandong Electric Power Group Corporation to develop a detection system, and proposed an algorithm which can detection of high-voltage transmission lines in the complex background. In the power line surveying, one of the important tasks is to accurately measure the distance between the power line and surrounding objects. Recently, airborne laser scanning system is applied in inspections, but its cost is very high. At the same time, the equipment is heavy and the operation is complex. In this paper, the goal of study is to extract the power lines in the image and to measure the distance between the power lines and the surrounding objects using photogrammetry, POS system, image feature extraction and so on. It ensures the safe operation of the power lines.
Engineering applications show that this method can effectively automatic extraction of high-voltage transmission line in the context of complex natural, and can achieve the purpose of real-time detection of transmission lines. The main content is listed as follows:
本文基于山东电力集团公司电力科学研究院无人直升机巡检系统项目的研究和工程应用,开发了一套检测系统,并提出了一种在复杂自然背景条件下,从无人直升机上拍摄的航空影像中实时检测高压输电线路的算法,实现了实时视频输电线路跟踪。该算法首先归纳和分析电力线在无人直升机航拍影像上的成像特征,通过改进的边缘检测算子与PCNN检测算法对电力线像素进行检测和效果比较,设计适合电力线像素检测的算子；然后利用基于先验知识的改进Hough变换算法检测直线段,再根据高压输电线路的特性,去除一些杂线,确定高压输电线路；最后,利用Kalman滤波对视频图像中的高压输电线路进行实时检测跟踪。
通过工程应用表明,该方法能有效地自动提取复杂自然背景下的高压输电线路,并能达到实时检测输电线路目的。
The rapid development of our national economy brings up higher requirement to the safe operation of infrastructures such as power transmission network. High-voltage power line inspection is very important and onerous job. Current method of manual-style inspection can not fully meet the requirement of the power industry development, and it brings great difficulties to the security, management and maintenance of power network. The inspection of power lines with remote sensing technology is the urgent needs of the electricity sector.
This paper based on research and engineering applications of unmanned helicopter inspection system of the Electric Power Research Institute of Shandong Electric Power Group Corporation to develop a detection system, and proposed an algorithm which can detection of high-voltage transmission lines in the complex background. In the power line surveying, one of the important tasks is to accurately measure the distance between the power line and surrounding objects. Recently, airborne laser scanning system is applied in inspections, but its cost is very high. At the same time, the equipment is heavy and the operation is complex. In this paper, the goal of study is to extract the power lines in the image and to measure the distance between the power lines and the surrounding objects using photogrammetry, POS system, image feature extraction and so on. It ensures the safe operation of the power lines.
Engineering applications show that this method can effectively automatic extraction of high-voltage transmission line in the context of complex natural, and can achieve the purpose of real-time detection of transmission lines. The main content is listed as follows:
引文
[1]赵建军.线路故障原因及预防措施[J].农村电气化.2004,(8)：32-33.
[2]韩祯祥,曹一家.电力系统的安全性及防治措施[J]电网技术,2004,28(9)：1-6.
[3]柴渊.电力遥感技术发展综述[J].电力勘测,2001,1：59-61.
[4]邵允临,曹晋恩,尚大伟.直升机巡检华北电网超高压输电线路[J].中国电力,2003,36(7)：35-37.
[5]赵鹏,邓春,袁亦超.应用直升飞机巡检输电线路[J].华北电力技术,2002(10)：1-3.
[6]李国兴.我国直升机电力作业的现状与发展[J].电力设备,2006,17(3)：41-44.
[7]张吴明,杨又华,阎广建等.机载多角度多光谱成像技术在电力系统中的应用[J].华中电力,2006,19(06)： 1-3.
[8]刘峻明,王鹏新等.机载多角度电力巡线系统中预警模型的设计与实现[J].电力系统自动化.2006,30(16)：81-85.
[9]Aggarwal N, Karl W C. Line detection in images through regularized Hough transform [J].IEEE Image Processing,2006,15(3):582-591.
[10]孙丰荣,刘积仁.快速霍夫变换算法[J].计算机学报,2001,24(10)：1102-1109.
[11]赵建泉.基于动态规划理论的高分辨率遥感影像道路边缘检测算法研究[D].南京：河海大学,2007.
[12]R.Nevatia,K.Price.Locating Structures in Aerial Images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1982,4(5):476-488.
[13]VenKateswar, V., Chellappa, R. Extracting Straight Lines in Aerial images [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1992, 14(11):1111-1114.
[14]M.Boldt, R.Weiss.Token-Based Extraction of Straight Lines[J].IEEE Transactions on System, Man Cybernetics.1989,19(7):1581-1594.
[15]Burns, J., Hanson, A., Risemen, E.Extracting Straight Lines [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1986,8(4):425-455.
[16]李朝阳.高压线路走廊特征物提取和高程计算研究[D].北京：北京邮电大学, 2006.
[17]Emmanuel P, Baltsavias. A comparison between photogrammetry and laser scanning[J].ISPRS Journal of Photogrammetry and Remote Sensing,1999, 54(2-3):83-84.
[18]Aggarwal N, Karl W C. Line detection in images through regularized Hough transform [J].IEEE Image Processing,2006,15(3):582-591.
[19]孙丰荣,刘积仁.快速霍夫变换算法[J].计算机学报,2001,24(10)：1102-1109.
[20]赵建泉.基于动态规划理论的高分辨率遥感影像道路边缘检测算法研究[D].南京：河海大学,2007.
[21]R.Nevatia,K.Price.Locating Structures in Aerial Images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1982,4(5):476-488.
[22]VenKateswar, V., Chellappa, R. Extracting Straight Lines in Aerial images [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1992, 14(11):1111-1114.
[23]M.Boldt, R.Weiss.Token-Based Extraction of Straight Lines[J].IEEE Transactions on System, Man Cybernetics.1989,19(7):1581-1594.
[24]Burns, J., Hanson, A., Risemen, E.Extracting Straight Lines [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1986,8(4):425-455.
[25]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].高等教育出版社,2003：107-114.
[26]Canny J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligent.1986,8(6):679-698.
[27]王植,贺赛先.一种基于Canny理论的自适应边缘检测方法[J].计算机图象图形学报,2004,9(8)：957-960.
[28]Otsu N.A Threshold Selection Method from gray level histogram [J].IEEE Trans.Man. Cybern.1979.SMC-9(1):62-69.
[29]Florence Tupin, Henri Maitre, Jean-Fran, et al. Detection of linear features in SAR images:application to road network extraction [J].IEEE Transactions on Geosciences and Remote Sensing,1998,36(2):434-453.
[30]杨将林.SAR图像滤波和边缘检测技术研究[D].西安：西北工业大学,2007.
[31]蔡克,杨忠,黄宵宁,等.一种新的直升机巡检系统电力线提取算法[J].计算机技 术与发展,2009,19(10)：113-116.
[32]李朝阳,阎广建,肖志强等.高分辨率航空影像中高压电力线的自动提取[J].中国图像图形学报,2007,12(6)：1011-1045.
[2]韩祯祥,曹一家.电力系统的安全性及防治措施[J]电网技术,2004,28(9)：1-6.
[3]柴渊.电力遥感技术发展综述[J].电力勘测,2001,1：59-61.
[4]邵允临,曹晋恩,尚大伟.直升机巡检华北电网超高压输电线路[J].中国电力,2003,36(7)：35-37.
[5]赵鹏,邓春,袁亦超.应用直升飞机巡检输电线路[J].华北电力技术,2002(10)：1-3.
[6]李国兴.我国直升机电力作业的现状与发展[J].电力设备,2006,17(3)：41-44.
[7]张吴明,杨又华,阎广建等.机载多角度多光谱成像技术在电力系统中的应用[J].华中电力,2006,19(06)： 1-3.
[8]刘峻明,王鹏新等.机载多角度电力巡线系统中预警模型的设计与实现[J].电力系统自动化.2006,30(16)：81-85.
[9]Aggarwal N, Karl W C. Line detection in images through regularized Hough transform [J].IEEE Image Processing,2006,15(3):582-591.
[10]孙丰荣,刘积仁.快速霍夫变换算法[J].计算机学报,2001,24(10)：1102-1109.
[11]赵建泉.基于动态规划理论的高分辨率遥感影像道路边缘检测算法研究[D].南京：河海大学,2007.
[12]R.Nevatia,K.Price.Locating Structures in Aerial Images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1982,4(5):476-488.
[13]VenKateswar, V., Chellappa, R. Extracting Straight Lines in Aerial images [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1992, 14(11):1111-1114.
[14]M.Boldt, R.Weiss.Token-Based Extraction of Straight Lines[J].IEEE Transactions on System, Man Cybernetics.1989,19(7):1581-1594.
[15]Burns, J., Hanson, A., Risemen, E.Extracting Straight Lines [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1986,8(4):425-455.
[16]李朝阳.高压线路走廊特征物提取和高程计算研究[D].北京：北京邮电大学, 2006.
[17]Emmanuel P, Baltsavias. A comparison between photogrammetry and laser scanning[J].ISPRS Journal of Photogrammetry and Remote Sensing,1999, 54(2-3):83-84.
[18]Aggarwal N, Karl W C. Line detection in images through regularized Hough transform [J].IEEE Image Processing,2006,15(3):582-591.
[19]孙丰荣,刘积仁.快速霍夫变换算法[J].计算机学报,2001,24(10)：1102-1109.
[20]赵建泉.基于动态规划理论的高分辨率遥感影像道路边缘检测算法研究[D].南京：河海大学,2007.
[21]R.Nevatia,K.Price.Locating Structures in Aerial Images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1982,4(5):476-488.
[22]VenKateswar, V., Chellappa, R. Extracting Straight Lines in Aerial images [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1992, 14(11):1111-1114.
[23]M.Boldt, R.Weiss.Token-Based Extraction of Straight Lines[J].IEEE Transactions on System, Man Cybernetics.1989,19(7):1581-1594.
[24]Burns, J., Hanson, A., Risemen, E.Extracting Straight Lines [J].IEEE Transactions on Pattern Analysis and Machine Intelligent.1986,8(4):425-455.
[25]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].高等教育出版社,2003：107-114.
[26]Canny J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligent.1986,8(6):679-698.
[27]王植,贺赛先.一种基于Canny理论的自适应边缘检测方法[J].计算机图象图形学报,2004,9(8)：957-960.
[28]Otsu N.A Threshold Selection Method from gray level histogram [J].IEEE Trans.Man. Cybern.1979.SMC-9(1):62-69.
[29]Florence Tupin, Henri Maitre, Jean-Fran, et al. Detection of linear features in SAR images:application to road network extraction [J].IEEE Transactions on Geosciences and Remote Sensing,1998,36(2):434-453.
[30]杨将林.SAR图像滤波和边缘检测技术研究[D].西安：西北工业大学,2007.
[31]蔡克,杨忠,黄宵宁,等.一种新的直升机巡检系统电力线提取算法[J].计算机技 术与发展,2009,19(10)：113-116.
[32]李朝阳,阎广建,肖志强等.高分辨率航空影像中高压电力线的自动提取[J].中国图像图形学报,2007,12(6)：1011-1045.