A UAV-Based Visual Inspection Method for Rail Surface Defects
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · 3D Surveying and Cultural Heritage · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China
School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China
Beijing Research Center of Urban Traffic Information Sensing and Service Technologies, Beijing 100044, China
References (49)
Show source-provided references
1. Railway track derailment inspection system using segmentation based fractal texture analysis10.21917/ijivp.2015.0155 ↗
2. Rail defects: An overview10.1046/j.1460-2695.2003.00693.x ↗
3. Rail corrugation: Characteristics, causes, and treatments10.1243/09544097JRRT264 ↗
4. Edwards, J.R., Hart, J.M., Sawadisavi, S., Resendiz, E., Barkan, C., and Ahuja, N. (2009, January 2–5). Advancements in Railroad Track Inspection Using Machine-Vision Technology. Proceedings of the AREMA Conference on American Railway and Maintenance of Way Association, Chicago, IL, USA.
5. A real-time visual inspection system for railway maintenance: Automatic hexagonal-headed bolts detection10.1109/TSMCC.2007.893278 ↗
6. Defect detection in solar modules using ICA basis images10.1109/TII.2012.2209663 ↗
7. An analysis of the simulated acoustic emission sources with different propagation distances, types and depths for rail defect detection10.1016/j.apacoust.2014.06.004 ↗
8. Electromagnetic tomography rail defect inspection
9. The Potential of Ultrasonic Surface Waves for Rail Inspection10.1063/1.1916682 ↗
10. Visual inspection and classification algorithm of rail surface defect
11. Automated visual inspection of railroad tracks10.1109/TITS.2012.2236555 ↗
12. Integrating the symmetry image and improved sparse representation for railway fastener classification and defect recognition10.1155/2015/462528 ↗
13. A review on non-destructive evaluation of rails: State-of-the-art and future development10.1243/09544097JRRT209 ↗
14. A real-time visual inspection system for discrete surface defects of rail heads10.1109/TIM.2012.2184959 ↗
15. A hierarchical extractor-based visual rail surface inspection system10.1109/JSEN.2017.2761858 ↗
16. Surface defect detection for high-speed rails using an inverse pm diffusion model10.1108/SR-03-2015-0039 ↗
17. Automatic detection of blurred images in UAV image sets10.1016/j.isprsjprs.2016.09.010 ↗
18. Mobile 3d mapping for surveying earthwork projects using an unmanned aerial vehicle (UAV) system10.1016/j.autcon.2014.01.004 ↗
19. Selecting patterns and features for between-and within-crop-row weed mapping using UAV-imagery10.1016/j.eswa.2015.10.043 ↗
20. Automatic detection of wind turbine blade surface cracks based on UAV-taken images10.1109/TIE.2017.2682037 ↗
21. A safe flight approach of the UAV in the electrical line inspection
22. Visual Inspection of Historical Buildings Using Micro UAV10.1051/matecconf/201710307003 ↗
23. Yuan, C., Liu, Z., and Zhang, Y. (2015, January 9–12). UAV-Based Forest Fire Detection and Tracking Using Image Processing Techniques. Proceedings of the 2015 International Conference on Unmanned Aircraft Systems (ICUAS), Denver, CO, USA.10.1109/ICUAS.2015.7152345 ↗
24. Bridge crack detection using multi-rotary UAV and object-base image analysis10.5194/isprs-archives-XLII-2-W6-311-2017 ↗
25. Arenella, A., Greco, A., Saggese, A., and Vento, M. (2017, January 5–7). In Real Time Fault Detection in Photovoltaic Cells by Cameras on Drones. Proceedings of the 14th International Conference on Image Analysis and Recognition, Montreal, QC, Canada.10.1007/978-3-319-59876-5_68 ↗
26. Xiao, Q., Zhang, Q., Wu, X., Han, X., and Li, R. (2017, January 17–19). Learning Binary Code Features for UAV Target Tracking. Proceedings of the 3rd IEEE International Conference on Control Science and Systems Engineering (ICCSSE), Beijing, China.10.1109/CCSSE.2017.8087896 ↗
27. Baykara, H.C., Bıyık, E., Gül, G., Onural, D., and Öztürk, A.S. (2017, January 6–8). Real-Time Detection, Tracking and Classification of Multiple Moving Objects in UAV Videos. Proceedings of the 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), Boston, MA, USA.10.1109/ICTAI.2017.00145 ↗
28. Radovic, M., Adarkwa, O., and Wang, Q. (2017). Object recognition in aerial images using convolutional neural networks. J. Imaging, 3.10.3390/jimaging3020021 ↗
29. Survey on enhancement methods for non-uniform illumination image
30. A visual detection system for rail surface defects10.1109/TSMCC.2012.2198814 ↗
31. A denoising algorithm of image for UAV based on wavelet transform and mean-value filtering
32. Effect of track irregularities on initiation and evolution of rail corrugation10.1016/j.jsv.2004.08.042 ↗
33. Über ein wichtiges psychophysiches grundgesetz und dessen beziehung zur schäzung der sterngrössen
34. On the foundations of vision modeling: I. Weber’s law and Weberized TV restoration10.1016/S0167-2789(02)00734-0 ↗
35. (2018, May 01). Available online: https://en.wikipedia.org/wiki/Contrast_(vision).
36. A threshold selection method from gray-level histograms10.1109/TSMC.1979.4310076 ↗
37. A new method for gray-level picture thresholding using the entropy of the histogram10.1016/0734-189X(85)90125-2 ↗
38. Image segmentation based on gray stretch and threshold algorithm10.1016/j.ijleo.2015.01.033 ↗
39. Image denoising with combination of wavelet transform and median filtering
40. Image denoising using combination of median filtering and wavelet transform
41. Study of straight line rail image edge detection based on improved hough
42. Li, Q., Tan, Y., Huayan, Z., Ren, S., Dai, P., and Li, W. (2016, January 8–12). A Visual Inspection System for Rail Corrugation Based on Local Frequency Features. Proceedings of the 2016 IEEE 14th International Conference on Dependable, Autonomic and Secure Computing, 14th International Conference on Pervasive Intelligence and Computing, 2nd International Conference on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech), Auckland, New Zealand.10.1109/DASC-PICom-DataCom-CyberSciTec.2016.19 ↗
43. Gilchrist, A.L. (1994). The psychophysics of contrast brightness. Lightness, Brightness, and Transparency, Lawrence Erlbaum Associates, Inc.
44. Lightness, brightness, and brightness contrast: 1. Illuminance variation10.3758/BF03211767 ↗
45. Visual Morphology10.1117/12.341081 ↗
46. Rafael, C., and Gonzalez, R.E.W. (2008). Digital Image Processing, Pearson Education, Inc.. [3rd ed.].
47. A new method for grey-level picture thresholding using the entropy of the histogram10.1016/0165-1684(80)90020-1 ↗
48. Entropic thresholding, a new approach10.1016/0146-664X(81)90038-1 ↗
49. Xu, W. (2015). Study on Defect Recognition for Rail Surface Based on Machine Vision. [Master’s Thesis, Beijing Jiaotong University].