ellibsЭлектронные библиотекиRussian Digital Libraries Journal1562-5419Казанский (Приволжский) федеральный университет10.26907/1562-5419-2025-28-4-829-951ellibs-590Research ArticleСтатьиЭкспериментальное исследование порогового метода HSV и нейронной сети U-Net в задаче распознавания пожаровExperimental Study of HSV Threshold Method and U-Net Neural Net-work in Fire Recognition TaskБобырьМаксим ВладимировичBobyrMaksim Vladimirovichmaxbobyr@gmail.comМилостнаяНаталья АнатольевнаMilostnayaNatalya Anatolyevnanat_mil@mail.ruБондаренкоБогдан АндреевичBondarenkoBogdan Andreevichsikersinko@gmail.comБобырьМаксим МаксимовичBobyrMaksim Maksimovichmmbobyr@gmail.comЮго-Западный государственный университетSouthwest State UniversityЮго-Западный государственный университетSouth-West State University202519122025284829951Copyright © Бобырь М.В., Милостная Н.А., Бондаренко Б.А., Бобырь М.М., 20252025Бобырь М.В., Милостная Н.А., Бондаренко Б.А., Бобырь М.М.Bobyr M.V., Milostnaya N.A., Bondarenko B.A., Bobyr M.M.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ellibs.elpub.ru/jour/article/view/590

Проведен сравнительный анализ методов сегментации изображений пожара с использованием пороговой обработки в цветовом пространстве HSV и нейронной сети U-Net. Цель исследования заключалась в оценке эффективности этих подходов по времени выполнения и точности детекции огня на основе метрик RMSE, IoU, Dice и MAPE. Эксперименты были проведены на четырех различных изображениях пожара с вручную подготовленными истинными масками пожаров. Результаты показали, что метод HSV обеспечивает высокую скорость обработки (0.0010–0.0020 с), но склонен к детекции не только огня, но и дыма, что снижает его точность (IoU 0.0863–0.3357, Dice 0.1588–0.5026). Нейронная сеть U-Net демонстрирует более высокую точность сегментации огня (IoU – до 0.6015, Dice – до 0.7512) за счет избирательного выделения пламени, однако требует значительно большего времени (1.2477–1.3733 с) и может недооценивать общую площадь пожара (MAPE – до 78.5840%). Визуальная оценка подтвердила различия в поведении методов: HSV захватывает дым как часть целевой области, тогда как U-Net фокусируется исключительно на огне. Выбор между методами зависит от приоритетов задачи: скорости или точности. Предложены направления дальнейших исследований, включая оптимизацию U-Net и разработку гибридных подходов.

A comparative analysis of image segmentation methods for fire detection was conducted using thresholding in the HSV color space and the U-Net neural network. The study aimed to evaluate the efficiency of these approaches in terms of execution time and fire detection accuracy based on RMSE, IoU, Dice, and MAPE metrics. Experiments were performed on four different fire images with manually prepared ground truth fire masks. The results showed that the HSV method offers high processing speed (0.0010–0.0020 s) but tends to detect not only fire but also smoke, reducing its accuracy (IoU 0.0863–0.3357, Dice 0.1588–0.5026). The U-Net neural network demonstrates higher fire segmentation accuracy (IoU up to 0.6015, Dice up to 0.7512) due to selective flame detection but requires significantly more time (1.2477–1.3733 s) and may underestimate the total fire area (MAPE up to 78.5840%). Visual assessment confirmed differences in methods' behavior: HSV captures smoke as part of the target area, while U-Net focuses exclusively on fire. The choice between methods depends on task priorities: speed or accuracy. Future research directions were proposed, including U-Net optimization and the development of hybrid approaches.

сегментированиелокализация пожаровHSV-сегментацияU-Netsegmentationfire localizationHSV segmentationU-NetReferencesWaldamichael F.G., Debelee T.G., Ayano Y.M. Coffee disease detection using a robust HSV color-based segmentation and transfer learning for use on smartphones // International Journal of Intelligent Systems/ 2022. Vol. 37, No. 8. P. 4967–4993. https://doi.org/10.1002/int.22747Waldamichael F.G., Debelee T.G., Ayano Y.M. Coffee disease detection using a robust HSV color-based segmentation and transfer learning for use on smartphones // International Journal of Intelligent Systems/ 2022. Vol. 37, No. 8. P. 4967–4993. https://doi.org/10.1002/int.22747Pratomo A.H., Kaswidjanti W., Nugroho A.S., Saifullah S. Parking detection system using background subtraction and hsv color segmentation // Bulletin of Electrical Engineering and Informatics. 2021. Vol. 10, No. 6. P. 3211–3219.Pratomo A.H., Kaswidjanti W., Nugroho A.S., Saifullah S. Parking detection system using background subtraction and hsv color segmentation // Bulletin of Electrical Engineering and Informatics. 2021. Vol. 10, No. 6. P. 3211–3219.https://doi.org/10.11591/eei.v10i6.3251https://doi.org/10.11591/eei.v10i6.3251Wang Y., Han Q., Li Y., Li Y. Video smoke detection based on multi-feature fusion and modified random forest // Engineering Letters. 2021. Vol. 29, No. 3. P. 1115–1122.Wang Y., Han Q., Li Y., Li Y. Video smoke detection based on multi-feature fusion and modified random forest // Engineering Letters. 2021. Vol. 29, No. 3. P. 1115–1122.Kokovkina V.A., Antipov V.A. Adaptivnaya segmentatsiya simvolov na avtomobil'nykh nomerakh // DSPA: Voprosy primeneniya tsifrovoy obrabotki signalov. 2016. T. 6, № 3. S. 663–666.Kokovkina V.A., Antipov V.A. Adaptivnaya segmentatsiya simvolov na avtomobil'nykh nomerakh // DSPA: Voprosy primeneniya tsifrovoy obrabotki signalov. 2016. T. 6, № 3. S. 663–666.Li Y., Ge M., Zhang S., Wang K. Adaptive Segmentation Algorithm for Subtle Defect Images on the Surface of Magnetic Ring Using 2D-Gabor Filter Bank // Sensors. 2024. Vol. 24, No. 3. https://doi.org/10.3390/s24031031Li Y., Ge M., Zhang S., Wang K. Adaptive Segmentation Algorithm for Subtle Defect Images on the Surface of Magnetic Ring Using 2D-Gabor Filter Bank // Sensors. 2024. Vol. 24, No. 3. https://doi.org/10.3390/s24031031Zhuykova Ye.G. Sravnitel'nyy analiz adaptivnogo metoda k-srednikh i porogovoy klasterizatsii // Perspektivy nauki. 2024. Т. 6(177). S. 92–98.Zhuykova Ye.G. Sravnitel'nyy analiz adaptivnogo metoda k-srednikh i porogovoy klasterizatsii // Perspektivy nauki. 2024. Т. 6(177). S. 92–98.Rezki M., Nurdiani S., Safitri R.A., Ihsan M.I.R. Iqbal M. Segmentasi Api dan Asap Pada Kebakaran Dengan Metode K-Means Clustering // Computer Science (CO-SCIENCE). 2022. Vol. 2, No. 1. P. 26–32. https://doi.org/10.31294/coscience.v2i1.849Rezki M., Nurdiani S., Safitri R.A., Ihsan M.I.R. Iqbal M. Segmentasi Api dan Asap Pada Kebakaran Dengan Metode K-Means Clustering // Computer Science (CO-SCIENCE). 2022. Vol. 2, No. 1. P. 26–32. https://doi.org/10.31294/coscience.v2i1.849Zimichev Ye.A., Kazanskiy N.L., Serafimovich P.G. Prostranstvennaya klassifikatsiya giperspektral'nykh izobrazheniy s ispol'zovaniyem metoda kla-sterizatsii k-means++// Komp'yuternaya optika. 2014. Т. 38, № 2. S. 281–286. https://doi.org/10.18287/0134-2452-2014-38-2-281-286Zimichev Ye.A., Kazanskiy N.L., Serafimovich P.G. Prostranstvennaya klassifikatsiya giperspektral'nykh izobrazheniy s ispol'zovaniyem metoda kla-sterizatsii k-means++// Komp'yuternaya optika. 2014. Т. 38, № 2. S. 281–286. https://doi.org/10.18287/0134-2452-2014-38-2-281-286Pereyra M., McLaughlin S. Fast Unsupervised Bayesian Image Segmentation with Adaptive Spatial Regularisation // IEEE Transactions on Image Processing. 2017. Vol. 26, No. 6. P. 2577–2587. https://doi.org/10.1109/TIP.2017.2675165Pereyra M., McLaughlin S. Fast Unsupervised Bayesian Image Segmentation with Adaptive Spatial Regularisation // IEEE Transactions on Image Processing. 2017. Vol. 26, No. 6. P. 2577–2587. https://doi.org/10.1109/TIP.2017.2675165Singh K.R., Neethu K.P., Madhurekaa K., Harita A., Mohan P. Parallel SVM model for forest fire prediction // Soft Computing Letters. 2021. Vol. 3. 100014.Singh K.R., Neethu K.P., Madhurekaa K., Harita A., Mohan P. Parallel SVM model for forest fire prediction // Soft Computing Letters. 2021. Vol. 3. 100014.https://doi.org/10.1016/j.socl.2021.100014https://doi.org/10.1016/j.socl.2021.100014Xiong D., Yan L. Early smoke detection of forest fires based on SVM image segmentation //Journal of Forest Science. 2019. Vol. 65, No. 4. P. 150–159. https://doi.org/10.17221/82/2018-JFSXiong D., Yan L. Early smoke detection of forest fires based on SVM image segmentation //Journal of Forest Science. 2019. Vol. 65, No. 4. P. 150–159. https://doi.org/10.17221/82/2018-JFSDemin N.S., Il'yasova N.Yu., Paringer R.A., Kirsh D.V. Primeneniye iskusstvennogo intellekta v oftal'mologii na primere resheniya zadachi se-manticheskoy segmentatsii izobrazheniya glaznogo dna // Komp'yuternaya optika. 2023. Т. 47, № 5. S. 824–831. https://doi.org/10.18287/2412-6179-CO-1283Demin N.S., Il'yasova N.Yu., Paringer R.A., Kirsh D.V. Primeneniye iskusstvennogo intellekta v oftal'mologii na primere resheniya zadachi se-manticheskoy segmentatsii izobrazheniya glaznogo dna // Komp'yuternaya optika. 2023. Т. 47, № 5. S. 824–831. https://doi.org/10.18287/2412-6179-CO-1283Gavrilov D.A. Issledovaniye primenimosti svertochnoy neyronnoy seti U-Net k zadache segmentatsii izobrazheniy aviatsionnoy tekhniki // Komp'yuternaya optika. 2021. Т. 45, № 4. S. 575–579. https://doi.org/10.18287/2412-6179-CO-804Gavrilov D.A. Issledovaniye primenimosti svertochnoy neyronnoy seti U-Net k zadache segmentatsii izobrazheniy aviatsionnoy tekhniki // Komp'yuternaya optika. 2021. Т. 45, № 4. S. 575–579. https://doi.org/10.18287/2412-6179-CO-804Mseddi W.S., Ghali R., Jmal M., Attia R. Fire Detection and Segmentation using YOLOv5 and U-NET // In European Signal Processing Conference (Vol. 2021-August, pp. 741–745). European Signal Processing Conference, EUSIPCO. 2021. https://doi.org/10.23919/EUSIPCO54536.2021.9616026Mseddi W.S., Ghali R., Jmal M., Attia R. Fire Detection and Segmentation using YOLOv5 and U-NET // In European Signal Processing Conference (Vol. 2021-August, pp. 741–745). European Signal Processing Conference, EUSIPCO. 2021. https://doi.org/10.23919/EUSIPCO54536.2021.9616026Bochkov V.S., Katayeva L.Yu., Maslennikov D.A., Kasparov I.V. Primeneniye arkhitektury glubokogo obucheniya U-Net dlya resheniya zadachi vydeleniya vysokotemperaturnykh zon pozhara na video // Trudy NGTU im. R.Ye. Alekseyeva. 2019. Т. 3 (126). S. 9–16. https://doi.org/10.46960/1816-210X_2019_3_9Bochkov V.S., Katayeva L.Yu., Maslennikov D.A., Kasparov I.V. Primeneniye arkhitektury glubokogo obucheniya U-Net dlya resheniya zadachi vydeleniya vysokotemperaturnykh zon pozhara na video // Trudy NGTU im. R.Ye. Alekseyeva. 2019. Т. 3 (126). S. 9–16. https://doi.org/10.46960/1816-210X_2019_3_9Bochkov V.S., Katayeva L.Yu., Maslennikov D.A. Tochnaya mnogoklasso-vaya segmentatsiya pozharov: podkhody, neyronnyye seti, skhemy segmentatsii // Iskusstvennyy intellekt i prinyatiye resheniy. 2024. Т. 3. S. 71–86. https://doi.org/10.14357/20718594240306Bochkov V.S., Katayeva L.Yu., Maslennikov D.A. Tochnaya mnogoklasso-vaya segmentatsiya pozharov: podkhody, neyronnyye seti, skhemy segmentatsii // Iskusstvennyy intellekt i prinyatiye resheniy. 2024. Т. 3. S. 71–86. https://doi.org/10.14357/20718594240306Barmpoutis P., Stathaki T., Dimitropoulos K., Grammalidis N. Early fire detection based on aerial 360-degree sensors, deep convolution neural networks and exploitation of fire dynamic textures // Remote Sensing, 2020. Vol. 12 (19). P. 1–17. https://doi.org/10.3390/rs12193177Barmpoutis P., Stathaki T., Dimitropoulos K., Grammalidis N. Early fire detection based on aerial 360-degree sensors, deep convolution neural networks and exploitation of fire dynamic textures // Remote Sensing, 2020. Vol. 12 (19). P. 1–17. https://doi.org/10.3390/rs12193177Panina V.S., Amelichev G.E. Primeneniye svertochnykh neyronnykh setey Mask R-CNN v intellektual'nykh parkovochnykh sistemakh // E-Scio. 2022. Т. 6(69). S. 425–432.Panina V.S., Amelichev G.E. Primeneniye svertochnykh neyronnykh setey Mask R-CNN v intellektual'nykh parkovochnykh sistemakh // E-Scio. 2022. Т. 6(69). S. 425–432.Begum S.R., S Y.D., M S.V.M. Mask R-CNN for fire detection // International Research Journal of Computer Science. 2021. Vol. 8, No. 7. P. 145–151. https://doi.org/10.26562/irjcs.2021.v0807.003Begum S.R., S Y.D., M S.V.M. Mask R-CNN for fire detection // International Research Journal of Computer Science. 2021. Vol. 8, No. 7. P. 145–151. https://doi.org/10.26562/irjcs.2021.v0807.003Zhou Y.C., Hu Z.Z., Yan K.X., Lin J.R. Deep Learning-Based Instance Segmentation for Indoor Fire Load Recognition // IEEE Access. 2021. Vol. 9. P. 148771–148782. https://doi.org/10.1109/ACCESS.2021.3124831Zhou Y.C., Hu Z.Z., Yan K.X., Lin J.R. Deep Learning-Based Instance Segmentation for Indoor Fire Load Recognition // IEEE Access. 2021. Vol. 9. P. 148771–148782. https://doi.org/10.1109/ACCESS.2021.3124831Tsalera E., Papadakis A., Voyiatzis I., Samarakou M. CNN-based, contextualized, real-time fire detection in computational resource-constrained environments // Energy Reports. 2023. Vol. 9. P. 247–257. https://doi.org/10.1016/j.egyr.2023.05.260Tsalera E., Papadakis A., Voyiatzis I., Samarakou M. CNN-based, contextualized, real-time fire detection in computational resource-constrained environments // Energy Reports. 2023. Vol. 9. P. 247–257. https://doi.org/10.1016/j.egyr.2023.05.260Nguyen T.H., Nguyen T.N., Ngo B.V. A VGG-19 Model with Transfer Learning and Image Segmentation for Classification of Tomato Leaf Disease // AgriEngineering. 2022. Vol. 4, No. 4. P. 871–887. https://doi.org/10.3390/agriengineering4040056Nguyen T.H., Nguyen T.N., Ngo B.V. A VGG-19 Model with Transfer Learning and Image Segmentation for Classification of Tomato Leaf Disease // AgriEngineering. 2022. Vol. 4, No. 4. P. 871–887. https://doi.org/10.3390/agriengineering4040056Almeida J.S., Huang C., Nogueira F.G., Bhatia S., De Albuquerque V.H.C. EdgeFireSmoke: A Novel Lightweight CNN Model for Real-Time Video Fire-Smoke Detection // IEEE Transactions on Industrial Informatics. 2022. Vol. 18, No. 11. P. 7889–7898. https://doi.org/10.1109/TII.2021.3138752Almeida J.S., Huang C., Nogueira F.G., Bhatia S., De Albuquerque V.H.C. EdgeFireSmoke: A Novel Lightweight CNN Model for Real-Time Video Fire-Smoke Detection // IEEE Transactions on Industrial Informatics. 2022. Vol. 18, No. 11. P. 7889–7898. https://doi.org/10.1109/TII.2021.3138752Jeong S.W., Yoo J. I-firenet: A lightweight CNN to increase generalization performance for real-time detection of forest fire in edge AI environments // Journal of Institute of Control, Robotics and Systems. 2020. Vol. 26, No. 9. P. 802–810. https://doi.org/10.5302/J.ICROS.2020.20.0033Jeong S.W., Yoo J. I-firenet: A lightweight CNN to increase generalization performance for real-time detection of forest fire in edge AI environments // Journal of Institute of Control, Robotics and Systems. 2020. Vol. 26, No. 9. P. 802–810. https://doi.org/10.5302/J.ICROS.2020.20.0033Nadeem M., Dilshad N., Alghamdi N.S., Dang L.M., Song H.K., Nam J., Moon H. Visual Intelligence in Smart Cities: A Lightweight Deep Learning Model for Fire Detection in an IoT Environment // Smart Cities. 2023. Vol. 6, No. 5. P. 2245–2259. https://doi.org/10.3390/smartcities6050103Nadeem M., Dilshad N., Alghamdi N.S., Dang L.M., Song H.K., Nam J., Moon H. Visual Intelligence in Smart Cities: A Lightweight Deep Learning Model for Fire Detection in an IoT Environment // Smart Cities. 2023. Vol. 6, No. 5. P. 2245–2259. https://doi.org/10.3390/smartcities6050103Ryu J., Kwak D. Flame detection using appearance‐based pre‐processing and convolutional neural network // Applied Sciences (Switzerland). 2021. Vol. 11, No. 11. https://doi.org/10.3390/app11115138Ryu J., Kwak D. Flame detection using appearance‐based pre‐processing and convolutional neural network // Applied Sciences (Switzerland). 2021. Vol. 11, No. 11. https://doi.org/10.3390/app11115138Roh J.-H., Min S.-H., Kong M. Flame Segmentation Characteristics of YCbCr Color Model Using Object Detection Technique // Fire Science and Engineering. 2023. Vol. 37, No. 6. P. 54–61. https://doi.org/10.7731/kifse.7c1d5c35Roh J.-H., Min S.-H., Kong M. Flame Segmentation Characteristics of YCbCr Color Model Using Object Detection Technique // Fire Science and Engineering. 2023. Vol. 37, No. 6. P. 54–61. https://doi.org/10.7731/kifse.7c1d5c35Wang X., Li M., Gao M., Liu Q., Li Z., Kou L. Early smoke and flame detection based on transformer // Journal of Safety Science and Resilience. 2023. Vol. 4, No. 3. P. 294–304. https://doi.org/10.1016/j.jnlssr.2023.06.002Wang X., Li M., Gao M., Liu Q., Li Z., Kou L. Early smoke and flame detection based on transformer // Journal of Safety Science and Resilience. 2023. Vol. 4, No. 3. P. 294–304. https://doi.org/10.1016/j.jnlssr.2023.06.002Bobyr M., Arkhipov A., Emelyanov S., Milostnaya N. A method for creating a depth map based on a three-level fuzzy model // Engineering Applications of Artificial Intelligence. 2023. Vol. 117. https://doi.org/10.1016/j.engappai.2022.105629Bobyr M., Arkhipov A., Emelyanov S., Milostnaya N. A method for creating a depth map based on a three-level fuzzy model // Engineering Applications of Artificial Intelligence. 2023. Vol. 117. https://doi.org/10.1016/j.engappai.2022.105629

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