Morphological Detection and Extraction of Rail Surface Defects

Rail inspection by means of a visual system has been a subject of a number of publications in recent years. The main requirements with regard to such a system are that it has to be fast, nondestructive, and accurate. This article presents a system for rail defect detection and shape extraction utilizing morphological operations. The proposed system is evaluated using publicly available rail surface discrete defects (RSDDs) data sets of Type-I and Type-II. Several versions of the system are compared, and the best one is reduced to just 17 basic morphological operations implementing defect detection, defect extraction, and false-positive (FP) reduction scheme. Two evaluation methods are considered, which is a pixel-level method and a defect-level method. 70% precision and 79% recall were obtained at the defect level for Type-I RSDD. Similarly, 82% precision and 89% recall were obtained at the defect level for Type-II RSDD. Experiments showed that the FP reduction scheme is effective for type II RSDD when considering defect-level results, and it increases precision by 7%–9% while maintaining the recall almost intact. The execution time of the morphological operations of the detection algorithm together with FP reduction is in the order of 50 ms on a usual laptop.

[1]  Qingyong Li,et al.  A Hierarchical Extractor-Based Visual Rail Surface Inspection System , 2017, IEEE Sensors Journal.

[2]  Mariusz Nieniewski.  Extraction of surface defects using morphological pyramid and watershed: example of ferrite cores , 2003 .

[3]  Shubin Li,et al.  Detection of rail surface defects based on CNN image recognition and classification , 2018, 2018 20th International Conference on Advanced Communication Technology (ICACT).

[4]  E. Deutschl,et al.  Defect detection on rail surfaces by a vision based system , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[5]  V. R. Vijaykumar,et al.  Rail defect detection using Gabor filters with texture analysis , 2015, 2015 3rd International Conference on Signal Processing, Communication and Networking (ICSCN).

[6]  R. Haralick,et al.  Multi-resolution Morphology , 2019 .

[7]  Mehmet Karakose,et al.  A vision based diagnosis approach for multi rail surface faults using fuzzy classificiation in railways , 2017, 2017 International Conference on Computer Science and Engineering (UBMK).

[8]  Alain Ploix,et al.  Textured images segmentation by a multiresolution morphological decomposition method , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[9]  Jianwu Dang,et al.  Real time detection system for rail surface defects based on machine vision , 2018, EURASIP Journal on Image and Video Processing.

[10]  Nicola Ancona,et al.  Filter-based feature selection for rail defect detection , 2004 .

[11]  Yong Qin,et al.  A UAV-Based Visual Inspection Method for Rail Surface Defects , 2018, Applied Sciences.

[12]  Yaonan Wang,et al.  Surface defect detection for high-speed rails using an inverse P-M diffusion model , 2016 .

[13]  Yong Qin,et al.  Research on Rail Surface Defect Detection Method Based on UAV Images , 2018, 2018 Prognostics and System Health Management Conference (PHM-Chongqing).

[14]  Li Liu,et al.  Defect Detection of Rail Surface with Deep Convolutional Neural Networks , 2018, 2018 13th World Congress on Intelligent Control and Automation (WCICA).

[15]  Qingyong Li,et al.  A Visual Detection System for Rail Surface Defects , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[16]  Qingyong Li,et al.  A Real-Time Visual Inspection System for Discrete Surface Defects of Rail Heads , 2012, IEEE Transactions on Instrumentation and Measurement.

[17]  Ling Xiong,et al.  Heavy rail surface defects detection based on the morphology of multi-scale and dual-structure elements , 2015, 2015 Chinese Automation Congress (CAC).

[18]  Mehmet Karaköse,et al.  Rail defect detection with real time image processing technique , 2016, 2016 IEEE 14th International Conference on Industrial Informatics (INDIN).

[19]  Liu Li,et al.  Rail Surface Defect Detection Method Based on YOLOv3 Deep Learning Networks , 2018, 2018 Chinese Automation Congress (CAC).

[20]  Daniel F. García,et al.  Inspection system for rail surfaces using differential images , 2017, 2017 IEEE Industry Applications Society Annual Meeting.

[21]  Mehmet Karakose,et al.  A New Computer Vision Based Method for Rail Track Detection and Fault Diagnosis in Railways , 2017 .

[22]  Xinhua Zhuang,et al.  The digital morphological sampling theorem , 1989, IEEE Trans. Acoust. Speech Signal Process..

[23]  Yaonan Wang,et al.  Automatic Visual Detection System of Railway Surface Defects With Curvature Filter and Improved Gaussian Mixture Model , 2018, IEEE Transactions on Instrumentation and Measurement.

[24]  Bart De Schutter,et al.  Deep convolutional neural networks for detection of rail surface defects , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[25]  Lei Jia,et al.  A Coarse-to-Fine Model for Rail Surface Defect Detection , 2019, IEEE Transactions on Instrumentation and Measurement.

[26]  David M. J. Tax,et al.  Semi-supervised rail defect detection from imbalanced image data , 2016 .

[27]  Alexander Toet,et al.  Morphological sampling , 1991, CVGIP Image Underst..

[28]  Christopher Ian Johnson.  Image processing techniques for the detection and characterisation of features and defects in railway tracks , 2013 .