Railway Fastener Defects Recognition Algorithm Based on Computer Vision

Abstract

Abstract-Railway fastener detection is an important task in railway maintenance to ensure safety. However, the earlier detection methods based on computer vision have good performance on missing fasteners, but they have weaker ability to recognize the partially worn ones. In this paper, we exploit the axis-symmetrical structure to generate the first and second symmetry sample of original testing fastener image, and integrate the first and second image for improved representation-based fastener recognition. The underlying advantages of the scheme are as follows: first, the symmetry image can somewhat overcome the difficulty that the lack of training and testing samples. Second, the symmetry image is helpful for representation-based fastener recognition and we can obtain an accurate judgment of the original testing image by integrate the corresponding judgments of two symmetry image. The experiment results show that our proposed method can achieve a rather high precision.

Visual Comfort at the Road Lighting on the Border Line

“…1. System that records and illuminates the pantograph catenary image [1][2][3][4] form, Sobel edge extraction, line segment detector, and batch algorithm conversion techniques [11][12][13][14][15][16][17][18][19][20][21][22][23][24].…”

Thermal Analysis In Fixed, Flowed And Airless Environment For Cooling In Led Luminaires

“…1. System that records and illuminates the pantograph catenary image [1][2][3][4] form, Sobel edge extraction, line segment detector, and batch algorithm conversion techniques [11][12][13][14][15][16][17][18][19][20][21][22][23][24].…”

Track Fastener Defect Detection Model Based on Improved YOLOv5s

“…Moreover, it is easily disturbed by factors such as lighting conditions, image noise, and tracking environment in actual detection and needs better generalization ability and robustness. Liu et al [9] extracted the fastener pyramidal gradient histogram and image local macro texture features and then used a support vector machine (SVM) to identify and classify the fastener defects. Ma et al [10] extracted the edge features of fasteners using a median filter, improved the Canny edge detection method, and matched the features of defective fasteners using feature templates to achieve real-time detection of fasteners.…”