sustainНадежностьDependability1729-26462500-3909RAMS Journal Limited liability company10.21683/1729-2646-2024-24-3-24-33sustain-603Research ArticleПРИМЕНЕНИЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ЗАДАЧАХ НАДЕЖНОСТИ И БЕЗОПАСНОСТИМЕНЕНИЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ЗАДАЧАХ НАДЕЖНОСТИ И БЕЗОПАСНОСТИПрименение преобразования Хафа для определения границы путей в задачах компьютерного зрения аппаратно-программного комплекса фиксации исполненного движенияUsing Hough transform to define track boundaries as part of machine vision by train traffic-tracking hardware and software systemsПолевскийИ. С.PolevskiyI. S.

Полевский Илья Сергеевич – главный эксперт

Нижегородская улица, дом 27, строение 1, г. Москва, 109029

Ilia S. Polevskiy, Chief Expert

27, bldg 1 Nizhegorodskaya St., Moscow, 109029

i.polevskiy@vniias.ruНаучно-исследовательский и проектно-конструкторский институт информатизации, автоматизации и связи на железнодорожном транспорте (АО «НИИАС»)РоссияResearch and Design Institute for Information Technology, Signalling, and Telecommunications in Railway Transportation (JSC NIIAS)Russian Federation2024140920242432433Copyright © Полевский И.С., 20242024Полевский И.С.Polevskiy I.S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.dependability.ru/jour/article/view/603

Цель. При решении задач компьютерного зрения для определения границ детектируемого объекта, как правило, используются методы семантической сегментации, которые требуют высокого вычислительного ресурса. Их использование повышает сложность реализации и увеличивает стоимость решений для внедряемых аппаратно-программных комплексов. В настоящей работе предлагается альтернативный метод определения границы сегментируемого объекта, в виде железнодорожного пути, для комплекса фиксации исполненного движения. Методы. Так как железнодорожный путь на изображении можно представить линией полинома n-порядка, то для решения задачи детектирования границы пути предлагается использовать приближения в виде прямых линий. В качестве метода детектирования прямых линий предлагается использовать преобразование Хафа, параметрическое пространство которого будет скомпоновано в соответствии с решаемой задачей. Заключение. Предложенная аппроксимация позволит отказаться от семантической сегментации и снизит вычислительную сложность нагрузки на аппаратуру.

Aim. In the context of machine vision, the problem of detected object boundary definition is usually solved using semantic segmentation that requires a high computational resource. Its application increases the complexity and the cost of the implemented hardware and software systems. This paper proposes an alternative method for defining the boundary of a segmented object, i.e., a railway track, for a train traffic tracking system. Methods. Since a railway track in an image can be represented by an n-th order polynomial, it is suggested to solve the problem of track boundary detection by using approximations in the form of straight lines. It is suggested using the Hough transform to detect straight lines. The former’s parametric space will be arranged in accordance with the problem to be solved. Conclusions. The proposed approximation will allow abandoning semantic segmentation and reduce the computational complexity and load.

фиксация исполненного движениякомпьютерное зрениемашинное обучениепреобразование Хафасемантическая сегментацияtrain traffic trackingmachine visionmachine learningHough transformsemantic segmentationReferencesLeCun Y., Boser B., Denker J.S. et al. Backpropagation Applied to Handwritten Zip Code Recognition // Neural Computation. 1989. Vol. 1(4). Pp. 541-551.LeCun Y., Boser B., Denker J.S. et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation 1989;1(4):541-551.Zhao H., Shi J., Qi X. et al. Pyramid scene parsing network // Proceedings of the IEEE conference on computer vision and pattern Recognition (CVPR). 2017. Jun. Pp. 2881-2890.Zhao H., Shi J., Qi X. et al. Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2017. Pp. 2881-2890.He K., Zhang X., Ren S. et al. Deep residual learning for image recognition // Proceedings of the IEEE conference on computer vision and pattern Recognition (CVPR). 2016. Jun. Pp. 770-778.He K., Zhang X., Ren S. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2016. Pp. 770-778.Chen L.-C., Zhu Y., Papandreou G. et al. Encoder-decoder with atrous separable convolution for semantic image segmentation // European Conference on Computer Vision (ECCV). 2016. Sep. Pp. 833-851.Chen L.-C., Zhu Y., Papandreou G. et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: European Conference on Computer Vision (ECCV); 2016. Pp. 833-851.Chollet F. Xception: Deep learning with depthwise separable convolutions // Proceedings of the IEEE conference on computer vision and pattern Recognition (CVPR). 2017. Jun. Pp. 1251-1258.Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern Recognition (CVPR); 2017. Pp. 1251-1258.Chen L.-C., Papandreou G., Kokkinos I. et al. Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018. Vol. 40(4). Pp. 834-848.Chen L.-C., Papandreou G., Kokkinos I. et al. Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence 2018;40(4):834-848.Hernández D., Cecilia J.M., Cano J.C. et al. Flood detection using real-time image segmentation from unmanned aerial vehicles on edge-computing platform // Remote Sensing. 2022. Vol. 14(1). P. 223.Hernández D., Cecilia J.M., Cano J.C. et al. Flood detection using real-time image segmentation from unmanned aerial vehicles on edge-computing platform. Remote Sensing 2022;14(1):223.Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image segmentation // Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2015: 18th International Conference. Munich: Springer International Publishing, 2015. Pp. 234-241.Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2015: 18th International Conference. Munich: Springer International Publishing; 2015. Pp. 234-241.Hough P.V. Method and means for recognizing complex patterns. US Patent No. 3,069,654 (1962).Hough P.V. Method and means for recognizing complex patterns. US Patent No. 3,069,654 (1962).Brady M.L., Yong W. Fast Parallel Discrete Approximation Algorithms for the Radon Transform // Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures (SPAA). 1992. Pp. 91-99.Brady M.L., Yong W. Fast Parallel Discrete Approximation Algorithms for the Radon Transform. In: Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures (SPAA); 1992. Pp. 91-99.Canny J. A computational approach to edge detection // IEEE Transactions on Pattern Analysis and Machine Intelligence. 1986. Vol. 8. Pp. 679-698.Canny J. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 1986;8:679-698.Sobel I. History and Definition of the Sobel Operator. 2014. URL: https://www.researchgate.net/publication/239398674_An_Isotropic_3x3_Image_Gradient_Operator (дата обращения: 24.06.2024).Sobel I. History and Definition of the Sobel Operator. (accessed 24.06.2024). Available at: https://www.researchgate.net/publication/239398674_An_Isotropic_3x3_Image_Gradient_Operator.Bradley D., Roth G. Adaptive thresholding using the integral image // Journal of graphics tools. 2007. Vol. 12(2). Pp. 13-21.Bradley D., Roth G. Adaptive thresholding using the integral image. Journal of graphics tools 2007;12(2):13-21.Cheng C., Kalloor J. Analysis of High Level implementations for Recursive Methods on GPUs. URL: https://people.eecs.berkeley.edu/~kubitron/courses/cs262a-F21/projects/reports/project16_report_ver3.pdf (дата обращения: 24.06.2024).Cheng C., Kalloor J. Analysis of High Level implementations for Recursive Methods on GPUs. (accessed 24.06.2024). Available at: https://people.eecs.berkeley.edu/~kubitron/courses/cs262a-F21/projects/reports/project16_report_ver3.pdf.Borgefors G. Distance transformations in digital images // Computer vision, graphics, and image processing. 1986. Vol. 34(3). Pp. 344-371.Borgefors G. Distance transformations in digital images. Computer vision, graphics, and image processing 1986;34(3):344-371.Murphy A.H. The Finley Affair: A Signal Event in the History of Forecast Verification // Weather and Forecasting. 1996. Vol. 11(1). Pp. 3-20.Murphy A.H. The Finley Affair: A Signal Event in the History of Forecast Verification. Weather and Forecasting 1996;11(1):3-20.Lee J.-T., Kim H.-U., Lee C. et al. Semantic line detection and its applications // The International Conference on Computer Vision (ICCV). 2017. Pp. 3229-3237.Lee J.-T., Kim H.-U., Lee C. et al. Semantic line detection and its applications. In: The International Conference on Computer Vision (ICCV); 2017. Pp. 3229-3237.Гольденберг Л.М., Матюшкин Б.Д. Цифровая обработка сигналов. М.: Радио и связь, 1985. 312 с.Goldenberg L.M., Matyushkin B.D. [Digital signal processing]. Moscow: Radio i sviaz; 1985. (in Russ.)

The authors declare that there are no conflicts of interest present.