Detection of railway track from image by heuristic method
Küçük Resim Yok
Tarih
2015
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Defects on the railway track occur due to the abrasive effects of time and usage. As the magnitude of the defects increases, uncomfortable travel appears. If the defects progress further they may cause derailment of the train. Detection of the defects are performed by manual inspection of the track, which cause ignorance of some of the defects. In this study a heuristic algorithm, which detects railway track from the images acquired by unmanned vehicle, is developed. Rails and sleepers of the railway track is detected with high accuracy from the images acquired in nadir direction. Images are de-noised by Gauss filter and edges are detected by Prewitt Edge Detection algorithm. By considering the geometric properties of the railway track and the brightness values of the edges, the Heuristic algorithm decides on which edges belong to railway track. In this study, inspection of railways is proposed by the images acquired by unmanned aerial vehicles and the automated detection of railway elements are realized as the first step of the railway inspection. © 2015 IEEE.
Açıklama
2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 -- 16 May 2015 through 19 May 2015 -- 113052
Anahtar Kelimeler
edge detection, heuristic algorithm, image analysis
Kaynak
2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 - Proceedings
WoS Q Değeri
Scopus Q Değeri
N/A
