ABSTRACT
The surface quality of steel rail is connected to the safety and service life of high-speed rail transportation, and its rail waist character is essential for logistical monitoring and quality traceability. At the moment, it is difficult to use the same set of equipment to recognize features and defects in three dimensions on the complicated surface of the rail. The ring stroboscopic illumination system was devised in this study based on the features of the complicated surface of the rail, and the whole surface image of the rail was gathered by seven linear scan cameras. Create a point cloud model of the rail surface, then re-calibrate the light source's direction based on the rail's fundamental geometry. The normal vector of the rail surface is then calculated to appropriately recreate the 3D surface of the rail. This research provides a method for eliminating gradient error in the direction of motion by using point cloud registration to increase the accuracy of 3D rail surface reconstruction. The breadth and depth of surface defects were assessed using the rail surface's rebuilt 3D model, and the average relative inaccuracy was 7.23%. The Yolo deep learning algorithm is utilized for character identification, and recognition accuracy may reach more than 99%. Experiments suggest that the approach may be used to detect rail surface defects in three dimensions on time. The method not only could be beneficial to the monitoring and optimization of the quality in the rail manufacturing process, but also establish a solid foundation for increasing the safety of high-speed trains.
- Tangbo Bai, Jialin Gao, Jianwei Yang, and Dechen Yao. 2021. A Study on Railway Surface Defects Detection Based on Machine Vision. Entropy-Switz. (2021), 1437. DOI 10.3390/e23111437Google Scholar
- Xuefeng Ni, Ziji Ma, Jianwei Liu, Bo Shi, and Hongli Liu. 2022. Attention Network for Rail Surface Defect Detection via Consistency of Intersection-over-Union(IoU)-Guided Center-Point Estimation. IEEE T. Ind. Inform. (2022), 1694-1705. DOI 10.1109/TII.2021.3085848Google Scholar
- Francisco J. DelaCalle, Daniel F. Garcia, and Ruben Usamentiaga. 2021. Rail Surface Inspection System Using Differential Topographic Images. IEEE T. Ind. Appl. (2021), 2994-3003. DOI 10.1109/TIA.2021.3059605Google Scholar
- Menghui Niu, Kechen Song, Liming Huang, Qi Wang, Yunhui Yan, and Qinggang Meng. 2021. Unsupervised Saliency Detection of Rail Surface Defects using Stereoscopic Images. IEEE T. Ind. Inform. (2021), 1. DOI 10.1109/TII.2020.3004397Google Scholar
- Mariusz Nieniewski. 2020. Morphological Detection and Extraction of Rail Surface Defects. IEEE T. Instrum. Meas. (2020), 6870-6879. DOI 10.1109/TIM.2020.2975454Google Scholar
- Jiang Hua Feng, Hao Yuan, Yun Qing Hu, Jun Lin, Shi Wang Liu, and Xiao Luo. 2020. Research on deep learning method for rail surface defect detection. IET Electrical Systems in Transportation (2020), 436-442. DOI 10.1049/iet-est.2020.0041Google Scholar
- Zhixin Hu, Hongtao Zhu, Ming Hu, and Yong Ma. 2018. Rail surface spalling detection based on visual saliency. IEEJ T. Electr. Electr. (2018), 505-509. DOI 10.1002/tee.22594Google Scholar
- Xiaohui Cao, Wen Xie, Siddiqui Muneeb Ahmed, and Cun Rong Li. 2020. Defect detection method for rail surface based on line-structured light. Measurement (2020), 107771. DOI 10.1016/j.measurement.2020.107771Google Scholar
- Xuefeng Ni, Ziji Ma, Jianwei Liu, Bo Shi, and Hongli Liu. 2022. Attention Network for Rail Surface Defect Detection via Consistency of Intersection-over-Union(IoU)-Guided Center-Point Estimation. IEEE T. Ind. Inform. (2022), 1694-1705. DOI 10.1109/TII.2021.3085848Google Scholar
- Zhou W, Kambhamettu C. A unified framework for scene illuminant estimation[J]. Image & Vision Computing, 2008, 26(3):415-429.Google ScholarDigital Library
- Esteban C H, Vogiatzis G, Cipolla R. Multiview Photometric Stereo[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2008, 30(3):548.Google ScholarDigital Library
- Wang Y, Samaras D. Estimation of multiple directional illuminants from a single image[J]. Image & Vision Computing, 2008, 26(9):1179-1195.Google ScholarDigital Library
- Julià C, Lumbreras F, Sappa A D. A factorization‐based approach to photometric stereo[J]. International Journal of Imaging Systems & Technology, 2015, 21(1):115-119.Google ScholarCross Ref
- Mukaigawa Y, Ishii Y, Shakunaga T. Analysis of photometric factors based on photometric linearization.[J]. Journal of the Optical Society of America A Optics Image Science & Vision, 2007, 24(10):3326-34.Google ScholarCross Ref
- Wu Z, Tan P. Calibrating Photometric Stereo by Holistic Reflectance Symmetry Analysis[C] IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2013:1498-1505.Google Scholar
- Quéau Y, Lauze F, Durou J D. Solving Uncalibrated Photometric Stereo Using Total Variation[J]. Journal of Mathematical Imaging & Vision, 2015, 52(1):87-107.Google ScholarDigital Library
- T. C. Wei, U. U. Sheikh and A. A. A. Rahman, "Improved optical character recognition with deep neural network,"[C]. 2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA), Batu Feringghi, 2018, pp. 245-249.Google ScholarCross Ref
- Yoshida M.and Eden M. Handwritten Chinese character recognition by an analysis by synthesis method[C]. Proc. 1st Int. J. Conf. Pattern Recognition, Washington, pp. 197-204 (2016).Google Scholar
- Nikitin I S, Usachev Y A. Research of recognition algorithm for sheet metal marking[C]. 2017 2nd International Ural Conference on Measurements (UralCon). IEEE, 2017: 130-137.Google Scholar
- Elagouni K, Garcia C, Mamalet F, Text recognition in multimedia documents: a study of two neural-based OCRs using and avoiding character segmentation[J]. International Journal on Document Analysis & Recognition, 2015,17(1):19-24.Google ScholarDigital Library
- Ali M, Foroosh H. Character recognition in natural scene images using rank-1 tensor decomposition[C]. IEEE International Conference on Image Processing. IEEE, 2016:2891-2895.Google Scholar
Recommendations
Filter-based feature selection for rail defect detection
Over the last few years research has been oriented toward developing a machine vision system for locating and identifying, automatically, defects on rails. Rail defects exhibit different properties and are divided into various categories related to the ...
Integrated scheduling of production and rail transportation
Nowadays, the most used, efficient and inexpensive mode of transportation between supply chain partners is the rail transportation. To the best of our knowledge, there is no research reported to date, which addresses the problem of synchronization of ...
Comments