<b>Wooden Sleeper Deterioration Evaluation System Using Image Analysis of Video</b>
-
- TSUBOKAWA Yosuke
- Track Geometry & Maintenance Laboratory, Track Technology Division
-
- KATO So
- Track Geometry & Maintenance Laboratory, Track Technology Division
-
- NAGAMINE Nozomi
- Image Analysis Laboratory, Information and Communication Technology Division
-
- GODA Wataru
- Image Analysis Laboratory, Information and Communication Technology Division
-
- MAEDA Riho
- Image Analysis Laboratory, Information and Communication Technology Division
-
- ITOI Kensuke
- Track Geometry & Maintenance Laboratory, Track Technology Division
Abstract
<p>This paper describes the development of a low-cost, simple system for inspecting wooden sleepers using images taken with a forward-facing handheld camera placed at the front of a train. This system is expected to save labor for inspecting track facilities. The system uses deep learning to classify the deterioration of wooden sleepers from images. In this paper, we report the outline of the system: classification accuracy, and verification results to see if the progress of deterioration can be assessed.</p>
Journal
-
- Quarterly Report of RTRI
-
Quarterly Report of RTRI 65 (1), 43-48, 2024-02-01
Railway Technical Research Institute
- Tweet
Details 詳細情報について
-
- CRID
- 1390862168253115904
-
- ISSN
- 18801765
- 00339008
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
-
- Abstract License Flag
- Disallowed