Application of the YOLO algorithm in fire and smoke detection systems for early detection of forest fires in real time

• Autorzy: Drzymała Agnieszka Joanna , Korzeniewska Ewa

Identyfikatory

DOI

10.15199/48.2025.02.11

Warianty tytułu

PL

Zastosowanie algorytmu YOLO w systemach procesu detekcji ognia i zadymienia dla potrzeb wczesnego wykrywania pożarów leśnych w czasie rzeczywistym

• Języki publikacji: EN

Abstrakty

EN

The paper presents a study of the possibilities of using modern machine learning methods based on the YOLO (You Only Look Once) algorithm in the detection and classification of fire hazards based on camera image recognition. The paper aims to develop an automation system for effectively identifying fire and smoke to develop effective protection of forest complexes. The YOLOv8 model was used in the detection process, which turned out to be a highly effective object detection model in real-time. The paper presents the process of preparing image data sets for the construction of the YOLO model. In the final part of the paper, many tests were carried out to assess the effectiveness and precision of the developed fire detection and fire prediction models. The results of these tests confirmed that the detection model works very precisely and can accurately identify fiery and smoky areas in camera images.

PL

W pracy zaprezentowano badanie możliwości zastosowania nowoczesnych metod uczenia maszynowego w oparciu o algorytm YOLO (You Only Look Once) w detekcji i klasyfikacji zagrożenia pożarowego na podstawie rozpoznawania obrazu pozyskanego z kamery. Praca ma na celu określenie efektywności działania algorytmu w automatyzacji identyfikacji ognia i zadymienia dla potrzeb opracowania skutecznej ochrony kompleksów leśnych. W procesie detekcji zastosowano model YOLOv8, który okazał się modelem wykrywania obiektów o wysokiej skuteczności w czasie rzeczywistym. W pracy zaprezentowano proces przygotowania zbiorów danych obrazowych dla potrzeb budowy modelu YOLO.

Słowa kluczowe

EN

YOLO; fire detection; deep learning; computer vision

PL

YOLO; wykrywanie pożaru; głębokie uczenie; analiza obrazu

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2025
• Tom: R. 101, nr 2
• Strony: 44--47
• Opis fizyczny: Bibliogr. 34 poz., rys.

Twórcy

autor

Drzymała Agnieszka Joanna

• Department of World Economy and European Integration, Institute of Economics, University of Lodz, 90-214 Lodz, Rewolucji 1905 Nr. 41, Poland

• https://orcid.org/0000-0003-1834-5202

autor

Korzeniewska Ewa

• Institute of Electrical Engineering Systems, Lodz University of Technology, Stefanowskiego, 90-537 Lodz, Poland

• https://orcid.org/0000-0002-0766-1376

Bibliografia

• [1] „Biodiversity strategy for 2030 - European Commission”. Access online: 27.10.2024. https://environment.ec.europa.eu/ strategy/biodiversity-strategy-2030_en
• [2] S. Singh, „“Forest fire emissions: A contribution to global climate change””, Front. For. Glob. Change, t. 5, lis. 2022, doi: 10.3389/ffgc.2022.925480.
• [3] M. Köhl, S. Linser, K. Prins, i A. Talarczyk, „The EU climate package “Fit for 55” - a double-edged sword for Europeans and their forests and timber industry”, Forest Policy and Economics, t. 132, s. 102596, lis. 2021, doi: 10.1016/j.forpol.2021.102596.
• [4] „Forest strategy - European Commission”. Access online: 27.10.2024. https://environment.ec.europa.eu/strategy/foreststrategy_ en
• [5] „Forests, forestry and logging”. Access online: 27.10.2024. https://ec.europa.eu/eurostat/statisticsexplained/ index.php?title=Forests,_forestry_and_logging
• [6] „Forest area”, European Environment Agency. Access online: 27.10.2024. https://www.eea.europa.eu/data-and-maps/data/ external/forest-area
• [7] „European Union". Access online: 27.10.2024. https://forest.eea.europa.eu/countries/regions/european-union
• [8] „FRA Platform | Global Forest Resources Data | Food and Agriculture Organization of the United Nations”. Access online: 27.10.2024. https://fra-data.fao.org/assessments/fra/2020/ EU27/home/overview/
• [9] „ROLA LASÓW W POCHŁANIANIU i MAGAZYNOWANIU WĘGLA Z ATMOSFERY”. Access online: 27.10.2024. https://siedlce.warszawa.lasy.gov.pl/aktualnosci/- /asset_publisher/t9xJ/content/rola-lasow-w-pochlanianiu-imagazynowaniu- wegla-z-atmosfery
• [10] Eurostat, „Eurostat: Area of wooded land”. Eurostat, 2024. doi: 10.2908/FOR_AREA_EFA.
• [11] G. R. van der Werf i in., „Global fire emissions estimates during 1997–2016”, Earth System Science Data, t. 9, nr 2, s. 697–720, wrz. 2017, doi: 10.5194/essd-9-697-2017.
• [12] P. Friedlingstein i in., „Global Carbon Budget 2022”, Earth System Science Data, t. 14, nr 11, s. 4811–4900, lis. 2022, doi: 10.5194/essd-14-4811-2022.
• [13] S. Calderara, P. Piccinini, i R. Cucchiara, „Vision based smoke detection system using image energy and color information”, Machine Vision and Applications, t. 22, nr 4, s. 705–719, lip. 2011, doi: 10.1007/s00138-010-0272-1.
• [14] S. Wang, X. Xiao, T. Deng, A. Chen, i M. Zhu, „A Sauter mean diameter sensor for fire smoke detection”, Sensors and Actuators B: Chemical, t. 281, s. 920–932, luty 2019, doi: 10.1016/j.snb.2018.11.021.
• [15] D. Pritam i J. H. Dewan, „Detection of fire using image processing techniques with LUV color space”, w 2017 2nd International Conference for Convergence in Technology (I2CT), kwi. 2017, s. 1158–1162. doi: 10.1109/I2CT.2017.8226309.
• [16] T. K. T. Nguyen i J.-M. Kim, „Multistage optical smoke detection approach for smoke alarm systems”, OE, t. 52, nr 5, s. 057001, maj 2013, doi: 10.1117/1.OE.52.5.057001.
• [17] Y. Chunyu, F. Jun, W. Jinjun, i Z. Yongming, „Video Fire Smoke Detection Using Motion and Color Features”, Fire Technol, t. 46, nr 3, s. 651–663, lip. 2010, doi: 10.1007/s10694-009-0110-z.
• [18] H. Cruz, M. Eckert, J. Meneses, i J.-F. Martínez, „Efficient Forest Fire Detection Index for Application in Unmanned Aerial Systems (UASs)”, Sensors, t. 16, nr 6, Art. nr 6, cze. 2016, doi: 10.3390/s16060893.
• [19] F. Yuan, „A double mapping framework for extraction of shapeinvariant features based on multi-scale partitions with AdaBoost for video smoke detection”, Pattern Recognition, t. 45, nr 12, s. 4326–4336, grudz. 2012, doi: 10.1016/j.patcog.2012.06.008.
• [20] T. X. Tung i J.-M. Kim, „An effective four-stage smoke-detection algorithm using video images for early fire-alarm systems”, Fire Safety Journal, t. 46, nr 5, s. 276–282, lip. 2011, doi: 10.1016/j.firesaf.2011.03.003.
• [21] Y. Chunyu, Z. Yongming, F. Jun, i W. Jinjun, „Texture Analysis of Smoke for Real-Time Fire Detection”, w 2009 Second International Workshop on Computer Science and Engineering, s. 511–515. doi: 10.1109/WCSE.2009.864.
• [22] F. Yuan, „Video-based smoke detection with histogram sequence of LBP and LBPV pyramids”, Fire Safety Journal, t. 46, nr 3, s. 132–139, 2011, doi: 10.1016/j.firesaf.2011.01.001.
• [23] Y. Qiao i in., „FireFormer: an efficient Transformer to identify forest fire from surveillance cameras”, Int. J. Wildland Fire, t. 32, nr 9, s. 1364–1380, 2023, doi: 10.1071/WF22220.
• [24] J. M. Johnston, L. M. Johnston, M. J. Wooster, A. Brookes, C. McFayden, i A. S. Cantin, „Satellite Detection Limitations of Sub- Canopy Smouldering Wildfires in the North American Boreal Forest”, Fire, t. 1, nr 2, Art. nr 2, 2018, doi: 10.3390/fire1020028.
• [25] J. Fernández-Berni i in., „Early forest fire detection by visionenabled wireless sensor networks”, Int. J. Wildland Fire, t. 21, nr 8, s. 938–949, lip. 2012, doi: 10.1071/WF11168.
• [26] J. Li, R. Xu, i Y. Liu, „An Improved Forest Fire and Smoke Detection Model Based on YOLOv5”, Forests, t. 14, nr 4, Art. nr 4, kwi. 2023, doi: 10.3390/f14040833.
• [27] S.-Y. Kim i A. Muminov, „Forest Fire Smoke Detection Based on Deep Learning Approaches and Unmanned Aerial Vehicle Images”, Sensors, t. 23, nr 12, Art. nr 12, 2023, doi: 10.3390/s23125702.
• [28] M. Hussain, „YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection”, Machines, t. 11, nr 7, Art. nr 7, 2023, doi: 10.3390/machines11070677.
• [29] Q. An, X. Chen, J. Zhang, R. Shi, Y. Yang, i W. Huang, „A Robust Fire Detection Model via Convolution Neural Networks for Intelligent Robot Vision Sensing”, Sensors, t. 22, nr 8, Art. nr 8, 2022, doi: 10.3390/s22082929.
• [30] H. Xu, B. Li, i F. Zhong, „Light-YOLOv5: A Lightweight Algorithm for Improved YOLOv5 in Complex Fire Scenarios”, Applied Sciences, t. 12, nr 23, Art. nr 23, 2022, doi: 10.3390/app122312312.
• [31] L. Zhang, J. Li, i F. Zhang, „An Efficient Forest Fire Target Detection Model Based on Improved YOLOv5”, Fire, t. 6, nr 8, Art. nr 8, 2023, doi: 10.3390/fire6080291.
• [32] H. Liu, H. Hu, F. Zhou, i H. Yuan, „Forest Flame Detection in Unmanned Aerial Vehicle Imagery Based on YOLOv5”, Fire, t. 6, nr 7, Art. nr 7, 2023, doi: 10.3390/fire6070279.
• [33] Mączka, M.; Hałdaś, G.; Pawłowski, S. QCL Active Area Modeling with a View to Being Applied to Chemical Substance Detection Systems. Sensors 2023, 23, 389. https://doi.org/10.3390/s23010389
• [34] „fire-smoke-datasets - v 1 2022-08-26 10:26pm > Images”, Roboflow. online: 01.10.2024. https://universe.roboflow.com/ buitems-ycaeh/fire-smoke-datasets