一种两点间直线搜索的输电线检测方法
|
摘要
在无人机应用于输电线巡检背景下,精准检测出图像中的输电线有助于后续的故障检测与分析;通过对计算机图形学中画圆算法研究,提出了一种两点间直线搜索的输电线检测方法:首先,通过方向可控滤波器对无人机图像进行分割;然后,通过所提出的基于圆搜索(CBS)直线段检测方法进行直线段检测;最后,通过所提出的基于格式塔原理的特征的直线连接方进行直线段连接;通过在人造图像上的实验可知:CBS直线检测方法中,半径参数需要足够大才能获得较好的检测效果;基于格式塔原理的特征的直线连接方法可以进一步提高检测性能;通过在无人巡线的真实图像上实验:验证了人造图像上实验所得出的结论仍然适用;且文章算法的检测准确率和误检率分别比Hough变换方法高出21.1%和低出11.4%;因此,文章算法是一种性能良好的基于无人机巡线图像的输电线检测方法。
Under the background of unmanned aerial vehicle(UAV)used in power line inspection,accurate detection of power lines in the image is helpful for subsequent fault detection and analysis.Researching the circle drawing algorithm based on computer graphics,this paper presents a new method of power line detection with line search between two points:firstly,the UAV image is segmented by Steerable filter;secondly,circle search(CBS)is used to detect the power line;finally,a straight line connection based on Gestalt principle is proposed to connect power lines.Experiments on man-made images show that the radius parameters of CBS line detection method need to be large enough to achieve better detection results;the linear connection method based on Gestalt principle can further improve detection performance.Experiments on real images of unmanned inspection line show that the experimental results on artificial images are still applicable,and the detection accuracy and false detection rate of this algorithm are 21.1% higher and 11.4%lower than that of Hough transform.Therefore,the algorithm is a good power line detection method based on UAV inspection line images.
Under the background of unmanned aerial vehicle(UAV)used in power line inspection,accurate detection of power lines in the image is helpful for subsequent fault detection and analysis.Researching the circle drawing algorithm based on computer graphics,this paper presents a new method of power line detection with line search between two points:firstly,the UAV image is segmented by Steerable filter;secondly,circle search(CBS)is used to detect the power line;finally,a straight line connection based on Gestalt principle is proposed to connect power lines.Experiments on man-made images show that the radius parameters of CBS line detection method need to be large enough to achieve better detection results;the linear connection method based on Gestalt principle can further improve detection performance.Experiments on real images of unmanned inspection line show that the experimental results on artificial images are still applicable,and the detection accuracy and false detection rate of this algorithm are 21.1% higher and 11.4%lower than that of Hough transform.Therefore,the algorithm is a good power line detection method based on UAV inspection line images.
引文
[1]李建峰,段宇涵,王仓继,等.无人机在输电线路巡检中的应用[J].电网与清洁能源,2017,33(8):62-65.
[2]王亚先,韩军,赵庆喜,等.关于无人机自动巡检方法的研究[J].计算机仿真,2017,34(3):56-61.
[3]吴立远,毕建刚,常文治,等.配网架空输电线路无人机综合巡检技术[J].中国电力,2018,51(1).
[4]Menendez O A,Perez M,Cheein F A A.Vision based inspection of transmission lines using unmanned aerial vehicles[A].IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems[C].IEEE.2017:412-417.
[5]Liao J,Zhang Q Y,Su Y,et al.Design of small four-rotor UAV transmission line inspection systems[A].International Conference on Machinery,Materials Engineering,Chemical Engineering and Biotechnology.[C].2016.
[6]Akinlar C,Topal C.EDLines:A real-time line segment detector with a false detection control[J].Pattern Recognition Letters,2011,32(13):1633-1642.
[7]Gioi R G V,Jakubowicz J,Morel J M,et al.LSD:A line segment detector[J].Image Processing on Line,2012,2(4):35-55.
[8]Hough P V C.Method and means for recognizing complex patterns[J].1962.
[9]Duda R O,Hart P E.Use of the Hough transformation to detect lines and curves in pictures[J].CACM,1972,15(1):11-15.
[10]Burns J B,Hanson A R,Riseman E M.Extracting straight lines[M].IEEE Computer Society,1986.
[11]Yao X,Guo L,Zhao T.Power Line Detection Based on Region Growing and Ridge-Based Line Detector[A].Proceedings of2013Chinese Intelligent Automation Conference[C].Springer Berlin Heidelberg,2013:431-437.
[12]John Canny.A Computational Approach to Edge Detection[J].1986:679-698.
[13]Li Z,Liu Y,Hayward R,et al.Knowledge-based power line detection for UAV surveillance and inspection systems[A].Image and Vision Computing New Zealand,2008.Ivcnz 2008.International Conference[C].IEEE,2009:1-6.
[14]Zhang J,Liu L,Wang B,et al.High Speed Automatic Power Line Detection and Tracking for a UAV-Based Inspection[A].International Conference on Industrial Control and Electronics Engineering[C].IEEE,2012:266-269.
[15]Li Zhengrong,Liu Yuee,Ross Hayward,et al.Knowledgebased power line detection for UAV surveillance and inspection systems[A].2008 23rd International Conference Image and Vision Computing New Zealand[C].pages 1-6,November 2008.
[16]Grompone v G R,Jakubowicz J,Morel J M,et al.LSD:a fast line segment detector with a false detection control[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2010,32(4):722-732.
[17]Philipp Heer.Framework for Vision-Based Power Line Inspection with an UAV[R].Technical report,2012.
[18]Cihan Topal and Cuneyt Akinlar.Edge Drawing:A combined real-time edge and segment detector[J].Journal of Visual Communication and Image Representation,23(6):862-872,August 2012.
[19]Young-Ho Choi,Tae-Kyeong Lee,and Se-Young Oh.Aline feature based SLAM with low grade range sensors using geometric constraints and active exploration for mobile robot[J].Autonomous Robots,24(1):13-27,October 2007.
[20]Freeman W T,Adelson E H.The design and use of steerable filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(9):891-906.
[21]Steger C.An unbiased detector of curvilinear structures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(2):113-125.
[22]Donald Hearn and M.Pauline Baker.Computer Graphics[M].Prentice Hall,1996
[23]Yuee Liu and Luis Mejias.Real-time Power Line Extraction from Unmanned Aerial System Video Images[A].In 2nd International Conference on Applied Robotics for the Power Industry(CARPI)[C].2012:52-57.
[2]王亚先,韩军,赵庆喜,等.关于无人机自动巡检方法的研究[J].计算机仿真,2017,34(3):56-61.
[3]吴立远,毕建刚,常文治,等.配网架空输电线路无人机综合巡检技术[J].中国电力,2018,51(1).
[4]Menendez O A,Perez M,Cheein F A A.Vision based inspection of transmission lines using unmanned aerial vehicles[A].IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems[C].IEEE.2017:412-417.
[5]Liao J,Zhang Q Y,Su Y,et al.Design of small four-rotor UAV transmission line inspection systems[A].International Conference on Machinery,Materials Engineering,Chemical Engineering and Biotechnology.[C].2016.
[6]Akinlar C,Topal C.EDLines:A real-time line segment detector with a false detection control[J].Pattern Recognition Letters,2011,32(13):1633-1642.
[7]Gioi R G V,Jakubowicz J,Morel J M,et al.LSD:A line segment detector[J].Image Processing on Line,2012,2(4):35-55.
[8]Hough P V C.Method and means for recognizing complex patterns[J].1962.
[9]Duda R O,Hart P E.Use of the Hough transformation to detect lines and curves in pictures[J].CACM,1972,15(1):11-15.
[10]Burns J B,Hanson A R,Riseman E M.Extracting straight lines[M].IEEE Computer Society,1986.
[11]Yao X,Guo L,Zhao T.Power Line Detection Based on Region Growing and Ridge-Based Line Detector[A].Proceedings of2013Chinese Intelligent Automation Conference[C].Springer Berlin Heidelberg,2013:431-437.
[12]John Canny.A Computational Approach to Edge Detection[J].1986:679-698.
[13]Li Z,Liu Y,Hayward R,et al.Knowledge-based power line detection for UAV surveillance and inspection systems[A].Image and Vision Computing New Zealand,2008.Ivcnz 2008.International Conference[C].IEEE,2009:1-6.
[14]Zhang J,Liu L,Wang B,et al.High Speed Automatic Power Line Detection and Tracking for a UAV-Based Inspection[A].International Conference on Industrial Control and Electronics Engineering[C].IEEE,2012:266-269.
[15]Li Zhengrong,Liu Yuee,Ross Hayward,et al.Knowledgebased power line detection for UAV surveillance and inspection systems[A].2008 23rd International Conference Image and Vision Computing New Zealand[C].pages 1-6,November 2008.
[16]Grompone v G R,Jakubowicz J,Morel J M,et al.LSD:a fast line segment detector with a false detection control[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2010,32(4):722-732.
[17]Philipp Heer.Framework for Vision-Based Power Line Inspection with an UAV[R].Technical report,2012.
[18]Cihan Topal and Cuneyt Akinlar.Edge Drawing:A combined real-time edge and segment detector[J].Journal of Visual Communication and Image Representation,23(6):862-872,August 2012.
[19]Young-Ho Choi,Tae-Kyeong Lee,and Se-Young Oh.Aline feature based SLAM with low grade range sensors using geometric constraints and active exploration for mobile robot[J].Autonomous Robots,24(1):13-27,October 2007.
[20]Freeman W T,Adelson E H.The design and use of steerable filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(9):891-906.
[21]Steger C.An unbiased detector of curvilinear structures[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(2):113-125.
[22]Donald Hearn and M.Pauline Baker.Computer Graphics[M].Prentice Hall,1996
[23]Yuee Liu and Luis Mejias.Real-time Power Line Extraction from Unmanned Aerial System Video Images[A].In 2nd International Conference on Applied Robotics for the Power Industry(CARPI)[C].2012:52-57.