Research on Railway Track Edge Detection Based on BM3D and Zernike Moments

• Autorzy: Wang Nan , Huo Tao , Zhang Tianming

Identyfikatory

DOI

10.61089/aot2023.fz9g6c16

• Języki publikacji: EN

Abstrakty

EN

With the rapid development of intelligent rail transportation, the realization of intelligent detection of railroad foreign body intrusion has become an important topic of current research. Accurate detection of rail edge location, and then delineate the danger area is the premise and basis for railroad track foreign object intrusion detection. The application of a single edge detection algorithm in the process of rail identification is likely to cause the problem of missing important edges and weak gradient change edges of railroad tracks. It will affect the subsequent detection of track foreign objects. A combined global and local edge detection method is proposed to detect the edges of railroad tracks. In the global pixel-level edge detection, an improved blok-matching and 3D filtering (BM3D) algorithm combined with bilateral filtering is used for denoising to eliminate the interference information in the complex environment. Then the gradient direction is added to the Canny operator, the computational template is increased to achieve non-extreme value suppression, and the Otsu thresholding segmentation algorithm is used for thresholding improvement. It can effectively suppress noise while preserving image details, and improve the accuracy and efficiency of detection at the pixel level. For local subpixel-level edge detection, the improved Zernike moment algorithm is used to extract the edges of the obtained pixel-level images and obtain the corresponding subpixel-level images. It can enhance the extraction of tiny feature edges, effectively reduce the computational effort and obtain the subpixel edges of the orbit images. The experimental results show that compared with other improved algorithms, the method proposed in this paper can effectively extract the track edges of the detected images with higher accuracy, better preserve the track edge features, reduce the appearance of pseudo-edges, and shorten the edge detection time with certain noise immunity, which provides a reliable basis for subsequent track detection and analysis.

Słowa kluczowe

EN

rail track; edge detection; BM3D; Zernike moments; Canny's operator

PL

tor kolejowy; krawędzie; BM3D; moment Zernika

• Wydawca: Warsaw University of Technology, Faculty of Transport
• Czasopismo: Archives of Transport
• Rocznik: 2023
• Tom: Vol. 68, iss. 4
• Strony: 7--20
• Opis fizyczny: Bibliogr. 31 poz., fot., rys., tab., wykr.

Twórcy

autor

Wang Nan

• School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, China

autor

Huo Tao

• School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, China

• https://orcid.org/0000-0002-7511-3013

autor

Zhang Tianming

• School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, China

Bibliografia

• [1] Archana, P., Karunakar, B., (2019). Image segmentation using improved Canny algorithm and mathematical morphology. Journal of Innovation in Electronics and Communication Engineering, 8(2), 48-53.
• [2] Burdzik, R., Nowak, B., Rozmus, J., Pawe Sowiński, Pankiewicz, J., (2017). Safety in the railway industry. Archives of Transport, 44(4), 15-24. https://doi.org/10.5604/01.3001.0010.6158
• [3] Cui, C. C., Zhou, X. C., Zan, M. Y., (2021). Image BM3D denoising method based on applying adaptive filtering. Electronic Measurement Technology, 44(12), 97-101.
• [4] Fu, J. H., Wang, J. P., Wen, L. H., et al. (2020).Bright-field stem cell image segmentation based on improved threshold and edge gradient. Electronic Measurement Technology, 43(20), 109-114.
• [5] Gong, S., Li, G., Zhang, Y., Li, C., Yu, L., (2019). Application of static gesture segmentation based on an improved canny operator. The Journal of Engineering, 2019(15), 543-546.https://doi.org/10.1049/joe.2018.9377
• [6] Goyal, B., Dogra, A., Sharma, A. M., (2020). BM3D outperforms major benchmarks in de noising: an argument in favor. Journal of Computer Science, 16(6), 838-847. https://doi.org/10.3844/jcssp.2020.838.847
• [7] Karolak, J., (2021). Interface and connection model in the railway traffic control system. Archives of Transport, 58(2), 137-147. https://doi.org/10.5604/01.3001.0014.9086
• [8] Liu, H. Z., Ning, J., Zou, Q. H., et al. (2022). Research on feature extraction technology of Mineral zoning image of spiral concentrator based on deep learning. Nonferrous Metals Engineering, 12(12), 91-99.
• [9] Liu, J., Zhao, J. Y., Chi, Y., (2021). Subpixel detection of weld center line based on Zernike moment algorithm. Journal of Shenyang Ligong University, 040(004), 1-5+10.
• [10] Liu, K., Li, L., Tan, F., (2020). A Design of Intelligent Foreign Object Intrusion Detection System in Subway Station Track Area. International conference on transportation engineering. https://doi.org/10.1061/9780784482742.126
• [11] Liu, Y., Cheng, M. M., Hu, X. W., Bai, X. et al. (2019). Richer convolutional features for edge detection. IEEE transactions on pattern analysis and machine intelligence, 41(8), 1939-1946. https://doi.org/10.1109/TPAMI.2018.2878849.
• [12] Luo, W. T., Li, Z. Y., Li, L., et al. (2018). Automated lane marking identification based on improved canny edge detection algorithm. Journal of Southwest Jiaotong University, 53(06), 1253-1260.
• [13] Lv, H., Shan, P., Shi, H., Zhao, L., (2022). An adaptive bilateral filtering method based on improved convolution kernel used for infrared image enhancement. Signal, Image and Video Processing, 16(8), 2231-2237. https://doi.org/10.1007/s11760-022-02188-1.
• [14] Niu, H. X., Hou, T., (2018). Fast detection study of foreign object intrusion on railway track. Archives of Transport, 47(3), 79-89. https://doi.org/10.5604/01.3001.0012.6510.
• [15] Ou, Y., Luo, J. Q., Xiong, Y., et al. (2020). Rivet size detection based on adaptive threshold Zernike moment. Transducer and Microsystem Technologies, 39(03), 139-142+152.
• [16] Polak, K., Korzeb, J., (2022). Modelling the acoustic signature and noise propagation of high speed railway vehicle. Archives of Transport, 64(4), 73-87. https://doi.org/10.5604/01.3001.0016.1051.
• [17] Ren, K. Q., Zhang, J. R., (2018). Extraction of plant leaf vein edges based on fuzzy enhancement and improved Canny. Journal of Optoelectronics&Laser, 29(11), 1251-1258.
• [18] Rosnelly, R., (2020). Combination of thresholding and Otsu method in increasing results of identification of malaria parasite type in thin blood smear image. International Journal of Psychosocial Rehabilitation, 24(4), 3807-3818. https://doi.org/10.37200/IJPR/V24I4/PR201494.
• [19] Sheshathri, V., Sukumaran, S., Manju, M., (2019). Improved Canny edge detection method for affected leaves. International Journal of Advanced Science and Technology, 28(17), 877-885.
• [20] Soilán, M., Nóvoa, A., Sánchez-Rodríguez, A., et al. (2021). Fully Automated Methodology for the Delineation of Railway Lanes and the Generation of IFC Alignment Models Using 3D Point Cloud Data. Automation in Construction, 126,103684. https://doi.org/10.1016/j.autcon.2021.103684.
• [21] Song, R. J., Liu, C., Wang, B. J., (2018). Adaptive Canny edge detection algorithm. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 38(03), 72-76.
• [22] Song, Y. F., Pan, D. F., Han, H., (2018). Track detection approach in complex environment based on saliency features. Journal of Railway Science and Engineering, 15(04), 871-879.
• [23] Tang, M. A., Wang, C. Y., (2021). Extraction of the edge of track images based on improved canny algorithm and hough transform. Railway Standard Design, 65(8), 60-64.
• [24] Wang, B., Wang, Z., Zhao, D., Wang, X. H., (2022). A rail detection algorithm for accurate recognition of train fuzzy video. Cyber-Physical Systems, 8(1), 67-84. https://doi.org/10.1080/23335777.2021.1879277.
• [25] Wang, Z. L., Cai, B. G., (2017). Geometry constraints-based method for visual rail track extraction. Journal of Transportation Systems Engineering and Information Technology, 17(06), 56-62, 84.
• [26] Wei, C. T., Yu, J. C., Zhao, P., et al. (2019). Automatic detection method of small cracks and micro grayscale difference cracks based on adaptive threshold. Journal of China and Foreign Highway, 39(01), 58-63.
• [27] Zhang, J. C., Xu X. G., Ye J., (2022). Image edge detection method based on improved Canny operator. Journal of Hainan Tropical Ocean University, 29(05), 79-84.
• [28]* Zhang, J. C., Xu, X. G., Ye, J., (2022). Image edge detection method based on improved Canny operator. Journal of Hainan Tropical Ocean University, 29(05), 79-84.
• [29] Zhang, Y. (2022). Research on rail identification based 3D point cloud. Qinhuangdao: Yanshan University.
• [30] Zheng, J. F., Gao, Y. C., Zhang, H., Lei, Y. Zhang, J., (2022). OTSU Multi-Threshold Image Segmentation Based on Improved Particle Swarm Algorithm. Applied Sciences. 12(22), 11514-11514. https://doi.org/10.3390/app122211514.
• [31] Zheng, Y. S., Yan, W. J., Yu, D., (2020). Rail detection based on LSD and the least square curve fitting. International Journal of Automation and Computing, 18(1), 1-11. https://doi.org/10.1007/s11633-020-1241-4.

Uwagi

* Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024)

* Bibliografia : zdublowane poz. 27 i 28.