PLD: Power line detection system for aircrafts

Power Line Detection (PLD) is still an important issue for aircraft safety. In this study, two simple PLD algorithms are developed that utilize two alternative line detection algorithms (EDLines and LSD) and feed their outputs to a simple K-Means classifier. The two versions are compared in terms of accuracy and speed. It was observed that, the newly developed EDLines method provides significantly superior results, thanks to its highly accurate edge detection. It is concluded that a method incorporating EDLines is expected to attract interest in PLD applications.

[1]  Ömer Emre Yetgin,et al.  Cable and wire detection system for aircrafts , 2013, 2013 21st Signal Processing and Communications Applications Conference (SIU).

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

[3]  Rangachar Kasturi,et al.  Wire Detection Algorithms for Navigation , 2002 .

[4]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[5]  Omer Emre Yetgin,et al.  A comparison of line detection methods for power line avoidance in aircrafts , 2015, 2015 9th International Conference on Electrical and Electronics Engineering (ELECO).

[6]  Tarak Gandhi,et al.  Real-time obstacle detection system for high speed civil transport supersonic aircraft , 2000, Proceedings of the IEEE 2000 National Aerospace and Electronics Conference. NAECON 2000. Engineering Tomorrow (Cat. No.00CH37093).

[7]  Yakup Genc,et al.  Edge Drawing: A Heuristic Approach to Robust Real-Time Edge Detection , 2010, 2010 20th International Conference on Pattern Recognition.

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

[9]  Cuneyt Akinlar,et al.  EDLines: A real-time line segment detector with a false detection control , 2011, Pattern Recognit. Lett..

[10]  Tarak Gandhi,et al.  Detection of obstacles in the flight path of an aircraft , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[12]  Ömer Nezih Gerek,et al.  Ground Truth of Power Line Dataset (Infrared-IR and Visible Light-VL) , 2017 .

[13]  Mark Savan,et al.  Retroreflectance of Wires and Cables at 10.6 Micrometers. , 1988 .

[14]  B. Barron,et al.  Low cost wire detection system , 1999, Gateway to the New Millennium. 18th Digital Avionics Systems Conference. Proceedings (Cat. No.99CH37033).

[15]  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.

[16]  Omer Emre Yetgin,et al.  Powerline Image Dataset (Infrared-IR and Visible Light-VL) , 2017 .

[17]  A. Kurdila,et al.  Vision-based control of micro-air-vehicles: progress and problems in estimation , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).