文章基本信息

标题：Semi-supervised Rail Defect Detection from Imbalanced Image Data
本地全文：下载
作者：Siamak Hajizadeh ; Alfredo Núñez ; David M.J. Tax 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2016
卷号：49
期号：3
页码：78-83
DOI：10.1016/j.ifacol.2016.07.014
语种：English
出版社：Elsevier
摘要：Abstract:Rail defect detection by video cameras has recently gained much attention in both academia and industry. Rail image data has two properties. It is highly imbalanced towards the non-defective class and it has a large number of unlabeled data samples available for semi-supervised learning techniques. In this paper we investigate if positive defective candidates selected from the unlabeled data can help improve the balance between the two classes and gain performance on detecting a specific type of defects called Squats. We compare data sampling techniques as well and conclude that the semi-supervised techniques are a reasonable alternative for improving performance on applications such as rail track Squat detection from image data.
关键词：Keywordsimbalance datasemi-supervised learningrail image datarail defect detection