A UAV-Based Visual Inspection Method for Rail Surface Defects
Rail surface defects seriously affect the safety of railway systems. At present, human inspection and rail vehicle inspection are the main approaches for the detection of rail surface defects. However, there are many shortcomings to these approaches, such as low efficiency, high cost, and so on. Thi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | http://www.mdpi.com/2076-3417/8/7/1028 |
id |
doaj-9f0c0ba85b534a85b8eb427a1356a5b7 |
---|---|
record_format |
Article |
spelling |
doaj-9f0c0ba85b534a85b8eb427a1356a5b72020-11-25T00:43:28ZengMDPI AGApplied Sciences2076-34172018-06-0187102810.3390/app8071028app8071028A UAV-Based Visual Inspection Method for Rail Surface DefectsYunpeng Wu0Yong Qin1Zhipeng Wang2Limin Jia3State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, ChinaState Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, ChinaState Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, ChinaState Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, ChinaRail surface defects seriously affect the safety of railway systems. At present, human inspection and rail vehicle inspection are the main approaches for the detection of rail surface defects. However, there are many shortcomings to these approaches, such as low efficiency, high cost, and so on. This paper presents a novel visual inspection approach based on unmanned aerial vehicle (UAV) images, and focuses on two key issues of UAV-based rail images: image enhancement and defects segmentation. With regards to the first aspect, a novel image enhancement algorithm named Local Weber-like Contrast (LWLC) is proposed to enhance rail images. The rail surface defects and backgrounds can be highlighted and homogenized under various sunlight intensity by LWLC, due to its illuminance independent, local nonlinear and other advantages. With regards to the second, a new threshold segmentation method named gray stretch maximum entropy (GSME) is presented in this paper. The proposed GSME method emphasizes gray stretch and de-noising on UAV-based rail images, and selects an optimal segmentation threshold for defects detection. Two visual comparison experiments were carried out to demonstrate the efficiency of the proposed methods. Finally, a quantitative comparison experiment shows the LWLC-GSME model achieves a recall of 93.75% for T-I defects and of 94.26% for T-II defects. Therefore, LWLC for image enhancement, in conjunction with GSME for defects segmentation, is efficient and feasible for the detection of rail surface defects based on UAV Images.http://www.mdpi.com/2076-3417/8/7/1028rail surface defectUAV imagedefect detectiongray stretch maximum entropyimage enhancementdefect segmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yunpeng Wu Yong Qin Zhipeng Wang Limin Jia |
spellingShingle |
Yunpeng Wu Yong Qin Zhipeng Wang Limin Jia A UAV-Based Visual Inspection Method for Rail Surface Defects Applied Sciences rail surface defect UAV image defect detection gray stretch maximum entropy image enhancement defect segmentation |
author_facet |
Yunpeng Wu Yong Qin Zhipeng Wang Limin Jia |
author_sort |
Yunpeng Wu |
title |
A UAV-Based Visual Inspection Method for Rail Surface Defects |
title_short |
A UAV-Based Visual Inspection Method for Rail Surface Defects |
title_full |
A UAV-Based Visual Inspection Method for Rail Surface Defects |
title_fullStr |
A UAV-Based Visual Inspection Method for Rail Surface Defects |
title_full_unstemmed |
A UAV-Based Visual Inspection Method for Rail Surface Defects |
title_sort |
uav-based visual inspection method for rail surface defects |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2018-06-01 |
description |
Rail surface defects seriously affect the safety of railway systems. At present, human inspection and rail vehicle inspection are the main approaches for the detection of rail surface defects. However, there are many shortcomings to these approaches, such as low efficiency, high cost, and so on. This paper presents a novel visual inspection approach based on unmanned aerial vehicle (UAV) images, and focuses on two key issues of UAV-based rail images: image enhancement and defects segmentation. With regards to the first aspect, a novel image enhancement algorithm named Local Weber-like Contrast (LWLC) is proposed to enhance rail images. The rail surface defects and backgrounds can be highlighted and homogenized under various sunlight intensity by LWLC, due to its illuminance independent, local nonlinear and other advantages. With regards to the second, a new threshold segmentation method named gray stretch maximum entropy (GSME) is presented in this paper. The proposed GSME method emphasizes gray stretch and de-noising on UAV-based rail images, and selects an optimal segmentation threshold for defects detection. Two visual comparison experiments were carried out to demonstrate the efficiency of the proposed methods. Finally, a quantitative comparison experiment shows the LWLC-GSME model achieves a recall of 93.75% for T-I defects and of 94.26% for T-II defects. Therefore, LWLC for image enhancement, in conjunction with GSME for defects segmentation, is efficient and feasible for the detection of rail surface defects based on UAV Images. |
topic |
rail surface defect UAV image defect detection gray stretch maximum entropy image enhancement defect segmentation |
url |
http://www.mdpi.com/2076-3417/8/7/1028 |
work_keys_str_mv |
AT yunpengwu auavbasedvisualinspectionmethodforrailsurfacedefects AT yongqin auavbasedvisualinspectionmethodforrailsurfacedefects AT zhipengwang auavbasedvisualinspectionmethodforrailsurfacedefects AT liminjia auavbasedvisualinspectionmethodforrailsurfacedefects AT yunpengwu uavbasedvisualinspectionmethodforrailsurfacedefects AT yongqin uavbasedvisualinspectionmethodforrailsurfacedefects AT zhipengwang uavbasedvisualinspectionmethodforrailsurfacedefects AT liminjia uavbasedvisualinspectionmethodforrailsurfacedefects |
_version_ |
1725278096220749824 |