韩冰,尚方
HAN Bing,SHANG Fang

• 1:黑龙江省电力科学研究院

摘要(Abstract)：

高压输电线路定期的巡逻检修是保障其安全可靠运行的重要手段。相比于传统的人工巡检,利用无人驾驶飞机搭载摄像机航拍的巡检方式具有速度快、人力成本低、人员风险小等优势。为了从海量的巡检图像中自动筛选出杆塔可能存在故障的图像,提出了一种融合多源信息的电力杆塔检测框架模型,主要包括摄像机标定、杆塔模型投影变换、杆塔模型聚类分析以及特征提取和匹配4个部分,并在实际的杆塔图像上进行了测试。结果表明,应用检测框架模型处理能够自动检测出图像中杆塔的精确位置,并判断杆塔是否存在杆件丢失等异常状态,验证了模型的有效性。
Regular inspection is key to operation safety and reliability of high-voltage transmission lines.Compared with the conventional manual inspection, inspection of UAV(unmanned aerial vehicle) with a camera for aerial photography is characterized by its fast speed, low labor cost, small personnel risk and so forth.In order to automatically select the images that may contain faulty power pylons from mass inspection images,the paper introduces a power pylon detection frame model that integrates multi-source information, including camera calibration, power pylon model projection transformation and cluster analysis as well as feature extraction and matching. Furthermore, the frame model is tested on actual pylon images. The results show that the frame model is able to automatically detect the precise power pylon location and determine abnormal status of power pylon such as member lost, which indicates the validity of the model.

关键词(KeyWords)： 电力杆塔;无人机;输电线路;巡检;图像
power pylon;unmanned aerial vehicle(UAV);transmission line;inspection;image

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 韩冰,尚方
HAN Bing,SHANG Fang

DOI: 10.19585/j.zjdl.2016.04.002

参考文献(References)：

• [1]DL/T 1006-2006架空输电线路巡检系统[S].北京:中国电力出版社,2007.
• [2]李贺.基于ARM的电力线巡检机器人运动控制器的研究[D].北京:华北电力大学,2008.
• [3]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(6):1-3.
• [4]赵利坡,范慧杰,朱琳琳,等.面向巡线无人机高压线实时检测与识别算法[J].小型微型计算机系统,2012,33(4):882-886.
• [5]Z R LI,Y LIU,A W RODNEY,F H ROSS,J L ZHANG.Towards Automatic Power Line Detection for a UAVSurveillance System Using Pulse Coupled Neural Filter and An Improved Hough Transform[J].Machine Vision and Applications,2009,21(5):677-686.
• [6]郭贞.基于快速高效启发式聚类算法的电力杆塔检测研究[D].北京:华北电力大学,2012.
• [7]B CETIN,M BIKDASH,M MCINERNEY.Automated Electric Utility Pole Detection from Aerial Images[J].Southeastcon,2009:44-49.
• [8]吴华,郭贞,杨国田,等.基于全局自相似描述子的电塔检测[J].华中科技大学学报(自然科学版),2011(39):437-440.
• [9]柳长安,叶文,吴华,等.融合地理位置信息的电力杆塔检测[J].华中科技大学学报(自然科学版),2013(39):208-211.
• [10]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报,2000,26(1):43-55.
• [11]王亮,吴福朝.基于一维标定物的多摄像机标定[J].自动化学报,2007,33(3):225-231.
• [12]Z ZHANG.A Flexible New Technique for Camera Calibration[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
• [13]J HEIKKIL魧.Geometric Camera Calibration Using Circular Control Points[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2000,22(10):1066-1077.
• [14]刘振亚主编.国家电网公司输变电工程通用设计―输电线路钢管塔分册[M].北京:中国电力出版社,2010.
• [15]J BOUGUET.Camera Calibration Toolbox for Matlab[OL].http://www.vision.caltech.edu/bouguetj/calib doc/,2015.
• [16]J Heikkil魧,O SILV′EN.A Four-step Camera Calibration Procedure with Implicit Image Correction[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,1997:1106-1112.
• [17]J R BEVERIDGE,E M RISEMAN.How Easy is Matching2D Line Models Using Local Search[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(6):564-579.
• [18]R G GIOI,J JAKUBOWICZ,J M MOREL,G RANDALL.LSD:A Fast Line Segment Detector with a False Detection Control[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2010,32(4):722-732.
• [19]R G GIOI,J JAKUBOWICZ,J M MOREL,G RANDALL.LSD:a Line Segment Detector[OL].Image Processing On Line,2012,2:35-55.
• [20]L L ZHANG,C XU,K M LEE,R KOCH.Robust and Efficient Pose Estimation from Line Correspondences[C].Proceedings of the 11th Asian Conference on Computer Vision,2012,217-230.