Reliability analysis of segmentation methods to identify the existence of railways (Case study: Yogyakarta international airport railway train)

View at publisher Summarise with VIRAT
Authors: M. Maharani, R. S. Arif, A. R. M. Syarif
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Segmentation method has shown a good level of success for detecting specific types of objects on the earths surface, but there has been no research examining the use of segmentation for detecting railway tracks. The purpose of this study is to test the reliability of the segmentation method in detecting specific objects in the form of railway track components using orthomosaic image data from aerial photography data acquisition with drones. The location chosen for the research was the construction of a new rail line from Kedundang station to Yogyakarta International Airport. This research using aerial photography equipped with GCP measurements using the RTK NTRIP GNSS receiver to obtain accurate coordinates. The results of the study showed that the segmentation method used couldn’t detect railway track components perfectly. The components that couldn’t be detected were railway track fasteners. However, the concrete and steel railway sleeper components could be detected well.

Fields of Study & Subjects

Infrastructure Maintenance and Monitoring Automated Road and Building Extraction Advanced Neural Network Applications

Publication details

Journal / source
AIP conference proceedings
Volume
3480
Pages
040024–040024
Publication date
1 January 2026
Language
EN