Publication Details

Effectiveness of Approaches for Rail Candidates Detection and Verification of the SVM

MUSIL Marek. Effectiveness of Approaches for Rail Candidates Detection and Verification of the SVM. In: ICTIC - Proceedings in Conference of Informatics and Management Sciences. Volume 5 Issue 1. Žilina: University of Žilina, 2016, pp. 152-156. ISBN 978-80-554-1196-5. Available from: http://www.ictic.sk/archive/?vid=1&aid=2&kid=50501-285
Czech title
Účinnost přístupu detekce kandidátů na kolejnice a ověření SVM
Type
conference paper
Language
english
Authors
Musil Marek, Ing. (DCGM FIT BUT)
URL
Keywords

rails detection,computer vision,Histogram of Oriented Gradients,pixel-per-pixel method,Support Vector Machine

Abstract

Rail candidates detection is the primary task in railway recognition systems based on recognition in images taken from the camera mounted on the board of the locomotive. In order to reduce the classifier complexity, effective and responsible rail candidates generation plays an important role without placing big decision responsibility on a further classifier stage. There are two basic options. Due to the rich complex environment along the track, pixel-per-pixel methods are often omitted. The second option involving a thorough investigation around a pixel is preferred. In this paper, we present comparison between two different approaches to rail candidates detection, each representing one of the basic groups, furthermore consequences in rail hypotheses generation. We introduce the finding that using the SVM is more efficient than the method based on pixel-per-pixel.

Published
2016
Pages
152-156
Proceedings
ICTIC - Proceedings in Conference of Informatics and Management Sciences
Series
Volume 5 Issue 1
Conference
ICTIC 2016, an International Virtual Conference, Žilina, SK
ISBN
978-80-554-1196-5
Publisher
University of Žilina
Place
Žilina, SK
DOI
BibTeX
@INPROCEEDINGS{FITPUB11174,
   author = "Marek Musil",
   title = "Effectiveness of Approaches for Rail Candidates Detection and Verification of the SVM",
   pages = "152--156",
   booktitle = "ICTIC - Proceedings in Conference of Informatics and Management Sciences",
   series = "Volume 5 Issue 1",
   year = 2016,
   location = "\v{Z}ilina, SK",
   publisher = "University of \v{Z}ilina",
   ISBN = "978-80-554-1196-5",
   doi = "10.18638/ictic.2016.5.1",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11174"
}
Back to top