Rail Surface Damage Detection Method Based on Improved U-Net Convolutional Neural Network

Bo Liang; Jun Lu; Yang Cao

doi:10.3788/LOP202158.0215009

[1] Resendiz E, Hart J M, Ahuja N. Automated visual inspection of railroad tracks[J]. IEEE Transactions on Intelligent Transportation Systems, 14, 751-760(2013). http://ieeexplore.ieee.org/document/6419832

[2] Shen X H, Li Z H, Li M et al. Aluminum surface-defect detection based on multi-task deep learning[J]. Laser & Optoelectronics Progress, 57, 101501(2020).

[3] Li S H, Zhou Y T, Wang D et al. Surface defect detection of polyvinyl chloride pipes based on machine vision[J]. Laser & Optoelectronics Progress, 56, 131006(2019).

[4] Chi H. On-line defect detection method of woven bag based on machine vision[J]. Laser & Optoelectronics Progress, 57, 201507(2020).

[5] Chen P H, Ho S S. Is overfeat useful for image-based surface defect classification tasks?. [C]∥2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, AZ, USA. New York: IEEE, 749-753(2016).

[6] Li D J, Li R H. Mug defect detection method based on improved Faster RCNN[J]. Laser & Optoelectronics Progress, 57, 041515(2020).

[7] Li Q Y, Tan Y Q, Zhang H Y et al. A visual inspection system for rail corrugation based on local frequency features. [C]∥2016 IEEE 14th Intl Conf on Dependable, Autonomic and Secure Computing, 14th Intl Conf on Pervasive Intelligence and Computing, 2nd Intl Conf on Big Data Intelligence and Computing and Cyber Scien, 18-23(2016).

[8] Caprioli A, Cigada A, Raveglia D. Rail inspection in track maintenance: a benchmark between the wavelet approach and the more conventional Fourier analysis[J]. Mechanical Systems and Signal Processing, 21, 631-652(2007).

[9] Trinh H, Haas N, Li Y et al. Enhanced rail component detection and consolidation for rail track inspection. [C]∥2012 IEEE Workshop on the Applications of Computer Vision (WACV), January 9-11, 2012, Breckenridge, CO, USA. New York: IEEE, 289-295(2012).

[10] Li Q Y, Ren S W. A real-time visual inspection system for discrete surface defects of rail heads[J]. IEEE Transactions on Instrumentation and Measurement, 61, 2189-2199(2012).

[11] Li Q Y, Ren S W. A visual detection system for rail surface defects[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42, 1531-1542(2012).

[12] He Z D, Wang Y N, Yin F et al. Surface defect detection for high-speed rails using an inverse P-M diffusion model[J]. Sensor Review, 36, 86-97(2016).

[13] Gan J R, Li Q Y, Wang J Z et al. A hierarchical extractor-based visual rail surface inspection system[J]. IEEE Sensors Journal, 17, 7935-7944(2017).

[14] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[M]. ∥Navab N, Hornegger J, Wells W, et al. Medical image computing and computer-assisted intervention-MICCAI 2015. Lecture notes in computer science. Cham: Springer, 9351, 234-241(2015).

[15] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE, 3431-3440(2015).

[16] Huang Y, Qiu C, Yuan K. Surface defect saliency of magnetic tile[J]. The Visual Computer, 36, 85-96(2020).