An automatic acquisition algorithm for power distribution line based on vehicle-mounted system

In order to realize automatic inspection of power distribution line and improve the safety of distribution network, a novel vehicle inspection system was designed, which contains visible-light camera, infrared imager and partial discharge detector. To ensure the effective information acquisition of equipments we expected to inspect, visual servo is used here to implement data automatic collection. An improved Edge Drawing Lines(EDLines) algorithm which gives fast and accurate results was proved to detect power lines in images. Based on the position of wire line in image, a reasonable pitch angle of pan-tilt can be adjusted automatically to realize the tracking process. On condition that GPS information of vehicle and power poles is given, a method of image capturing for pole and tower using image-based servo system is proposed, which provides the clear and the integrated images. Faster-RCNN algorithm is adopted here for detection and location of electric power tower in images. The experimental results demonstrate that the approach is effective for automatic inspection data collection of power distribution line and has a good application value.

[1]  R. Zapata,et al.  Flying among obstacles , 1999, 1999 Third European Workshop on Advanced Mobile Robots (Eurobot'99). Proceedings (Cat. No.99EX355).

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Rafael Grompone von Gioi,et al.  LSD: A Fast Line Segment Detector with a False Detection Control , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[7]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[8]  Sudeep Sarkar,et al.  Comparison of Edge Detectors: A Methodology and Initial Study , 1998, Comput. Vis. Image Underst..

[9]  Erkki Oja,et al.  Houghtool -- A software package for the use of the Hough transform , 1996, Pattern Recognit. Lett..

[10]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2015, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Cuneyt Akinlar,et al.  Edlines: Real-time line segment detection by Edge Drawing (ed) , 2011, 2011 18th IEEE International Conference on Image Processing.

[12]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Li Fu,et al.  Obstacle detection algorithms for aviation , 2011, 2011 IEEE International Conference on Computer Science and Automation Engineering.

[14]  X Zhang Image mosaic approach of transmission tower based on saliency map , 2015 .

[15]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[16]  Janos Toth,et al.  Smart view for a smart grid — Unmanned Aerial Vehicles for transmission lines , 2010, 2010 1st International Conference on Applied Robotics for the Power Industry.

[17]  Sudeep Sarkar,et al.  Comparison of edge detectors: a methodology and initial study , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Li Li,et al.  The application of image based visual servo control system for smart guard , 2013, 2013 10th IEEE International Conference on Control and Automation (ICCA).

[20]  Rafael Grompone von Gioi,et al.  On Straight Line Segment Detection , 2008, Journal of Mathematical Imaging and Vision.