Abstract: Insulators are the key components of high speed railway catenaries. Insulator failures can cause outages and affect the safe operation of high speed railways. It is important to perform insulator defect detection. Due to the collection of insulator images by moving catenary inspection vehicles, the consistency of the images is poor, and the number of insulator defect samples is very small. An algorithm of deep learning and conventional template matching cannot meet the requirements of insulator defect detection. This paper proposes a fusion algorithm based on the shed contour features and gray similarity matching. High accuracy and consistency of contour extraction and precise separation of each insulator shed were realized. An insulator defect detection model based on the spacing distance of the sheds and the gray similarity was constructed. Experiments show that the method based on the contour features and gray similarity matching can effectively classify normal insulators and defective insulators. Recall of 99.50% and high precision of 91.71% were achieved in the test of the image data set, and this can meet the requirements for the reliability and high precision of a detection algorithm for catenary insulators.

基于轮廓特征及灰度相似度匹配的接触网绝缘子缺陷检测

[1]Ai JY, Jin LJ, 2016. Rod porcelain insulator filth state detection of catenary based on ultraviolet image. Transactions of China Electrotechnical Society, 31(10):112-118 (in Chinese).

[2]Briechle K, Hanebeck U, 2001. Template matching using fast normalized cross correlation. Proceedings of the SPIE 4387, Optical Pattern Recognition XII, p.95-102.

[3]Canny J, 1986. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8(6):679-698.

[4]Chen RP, Chen JM, Wang HL, 2014. Recent research on the track-subgrade of high-speed railways. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 15(12):1034-1038.

[5]Dang ST, Ke J, Wu WH, et al., 2019. The contamination status anomaly detection of railway insulator based on PCM and texture feature. Insulators and Surge Arresters, (2):197-201 (in Chinese).

[6]Guo XG, Liu ZG, Zhang GN, et al., 2015. Fault detection of catenary insulator based on corner matching and image differencing. Proceedings of the CSU-EPSA, 27(2):8-14 (in Chinese).

[7]Haralick RM, 1984. Digital step edges from zero crossing of second directional derivatives. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-6(1):58-68.

[8]Pellegrino FA, Vanzella W, Torre V, 2004. Edge detection revisited. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 34(3):1500-1518.

[9]Rosenfeld A, Kak AC, 1982. Digital Picture Processing, 2nd Edition. Academic Press, San Diego, USA.

[10]Suzuki S, be K, 1985. Topological structural analysis of digitized binary images by border following. Computer Vision, Graphics, and Image Processing, 30(1):32-46.

[11]Tan P, 2014. Studies on Key Technologies of Safety and Intelligent Control for Intercity Railway On-board Train Control Systems. PhD Thesis, Zhejiang University, Hangzhou, China (in Chinese).

[12]Tan P, Ma JE, Zhou J, et al., 2016. Sustainability development strategy of China’s high speed rail. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 17(12):923-932.

[13]Wan GH, 2013. Unified information platform of traction power supply for the center with 6C system. Value Engineering, 32(13):197-198 (in Chinese).

[14]Wu J, Ye XQ, Gu WK, 2007. An adaptive fuzzy filter for coding artifacts removal in video and image. Journal of Zhejiang University-SCIENCE A, 8(6):841-848.

[15]Wu T, Wang WB, Yu L, et al., 2019. Insulator defect detection method for lightweight YOLOV3. Computer Engineering, 45(8):275-280 (in Chinese).

[16]Yang L, Zhang F, Bi JK, et al., 2018. Wetting characteristics and influential factors of pollution deposited on insulators based on phase angle difference. High Voltage Engineering, 44(8):2556-2564 (in Chinese).

[17]Yang QJ, Niu ZY, Feng XY, et al., 2019. Sobel improved algorithm for insulator ceramic crack recognition. Journal of Heilongjiang University of Science and Technology, 29(2):190-195 (in Chinese).

[18]Yao XT, Zhang YP, Gao Y, et al., 2018. Research on vision-based technology of contamination detection in overhead line insulators. Journal of Lanzhou Jiaotong University, 37(1):65-72 (in Chinese).

[19]Zhang GN, Liu ZG, 2014. Fault detection of catenary insulator damage/foreign material based on corner matching and spectral clustering. Chinese Journal of Scientific Instrument, 35(6):1370-1377 (in Chinese).

[20]Zhang QS, Zhu SC, 2018. Visual interpretability for deep learning: a survey. Frontiers of Information Technology & Electronic Engineering, 19(1):27-39.

[21]Ziou D, Tabbone S, 1998. Edge detection techniques: an overview. International Journal of Pattern Recognition and Image Analysis, 8(4):537-559.