Performance Benchmarking of YOLOv11, YOLOv12, and YOLOv26 for Real-Time Fire and Smoke Detection
DOI:
https://doi.org/10.32492/nucleus.v5i2.5219Keywords:
Yolov11, Yolov12, Yolov26, Deep Learning, Fire and Smoke Detection, Real-Time Object DetectionAbstract
Fire is a destructive event that causes significant losses; therefore, an accurate and rapid early fire detection system is essential. With advancements in computer vision technology, deep learning-based object detection methods are increasingly employed for real-time fire detection. This study aims to evaluate and compare the performance of You Only Look Once (YOLO) based models specifically YOLOv11, YOLOv12, and YOLOv26 in detecting fire and smoke objects in real-time using cameras, and to identify the optimal model based on evaluation results. The dataset consists of fire imagery categorized into two primary classes: fire and smoke. All three models were trained using identical configurations: an image size of 640 × 640 pixels, a batch size of 8, and 100 epochs on Google Colab. Performance was evaluated using precision, recall, F1-score, accuracy, mAP, and confusion matrices. Training results indicate that YOLOv11 achieved the highest mAP@50 value (approximately 0.52), compared to YOLOv12 (0.47) and YOLOv26 (0.50). In real-time testing, YOLOv11 achieved 93.3% accuracy, followed by YOLOv26 at 92.6% and YOLOv12 at 90.11%. Based on these results, YOLOv11 demonstrated the best performance under the experimental conditions, achieving the highest real-time accuracy and mAP@50 for both object classes. However, smoke detection remains a major challenge for Convolutional Neural Network-based fire detection systems due to smoke's dynamic, semi-transparent, and low-contrast characteristics. Consequently, the YOLOv11 model holds potential as a foundation for developing effective real-time fire detection systems, such as those for embedded systems, intelligent surveillance, and UAV-based platforms.
References
I. W. S. Gede et al., “Deteksi api kebakaran berbasis computer vision dengan algoritma YOLO,” Journal of Applied Mechanical Engineering and Green Technology, vol. 3, pp. 53–58, 2022, [Online]. Available: https://ojs2.pnb.ac.id/index.php/JAMETECH
N. D. H. Manurung, R. Khana, J. Muliadi, and M. Sobirin, “SISTEM DETEKSI KEBAKARAN BERBASIS VISI KOMPUTER DENGAN YOLOv11 TERINTEGRASI DENGAN TELEGRAM,” Transmisi: Jurnal Ilmiah Teknik Elektro, vol. 27, no. 4, pp. 240–248, 2025, doi: 10.14710/transmisi.27.4.240-248.
M. T. Fadlol, A. Khumaidi, L. Subiyanto, Joko Endrasmono, Mustika Kurnia Mayangsari, and Anggarjuna Puncak Pujiputra, “Penerapan Deteksi Titik Api Pada Area graving dock Menggunakan YOLO dan GRAD-CAM,” Jurnal Elektronika dan Otomasi Industri, vol. 12, no. 1, pp. 162–172, 2025, doi: 10.33795/elkolind.v12i1.7253.
M. A. M. Alsafy et al., “SISTEM DETEKSI DINI KEBAKARAN MELALUI ASAP BERBASIS COMPUTER VISION,” Front. Vet. Sci., vol. 13, no. 1, pp. 1–16, 2025, [Online]. Available: https://doi.org/10.1038/s41598-022-26846-z%0Ahttp://dx.doi.org/10.1038/s41467-021-22308-8%0Ahttps://doi.org/10.1007/s00253-025-13460-y%0Ahttps://doi.org/10.1016/j.heliyon.2023.e14088%0Ahttps://doi.org/10.1016/j.sjbs.2017.10.019%0Ahttps://doi.org/10.1016/j
L. T. Ramos, E. Casas, C. Romero, F. Rivas-Echeverría, and E. Bendek, “A study of YOLO architectures for wildfire and smoke detection in ground and aerial imagery,” Results in Engineering, vol. 26, no. December 2024, p. 104869, 2025, doi: 10.1016/j.rineng.2025.104869.
X. Geng, X. Han, X. Cao, Y. Su, and D. Shu, “YOLOV9-CBM: An Improved Fire Detection Algorithm Based on YOLOV9,” IEEE Access, vol. 13, pp. 19612–19623, 2025, doi: 10.1109/ACCESS.2025.3534782.
C. Science, “Fire Detection Using Single Shoot MultiBox Detector Algorithm with RGB Rule and YCbCr Rule Deteksi Kebakaran Menggunakan Algoritma Single Shoot MultiBox Detector dengan Rule RGB dan Rule YcbCr,” Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. January, pp. 391–404, 2025.
NEYZSA AMANDA, “Rancang Bangun Alat Pendeteksi Titik Api dan Asap Menggunakan Metode YOLO dan Berbasis Android untuk D,” vol. 1, no. 2809, pp. 193–197, 2021.
P. Dickens and T. M. S. Mulyana, “Fire Detection Using Logistic Regression with GLCM, RGB Ratio, RGB Intersection, and Color Moments,” Jurnal Ilmu Komputer dan Informatika, vol. 5, no. 1, pp. 33–42, 2025, doi: 10.54082/jiki.250.
L. T. Ramos, E. Casas, C. Romero, F. Rivas-Echeverría, and E. Bendek, “A study of YOLO architectures for wildfire and smoke detection in ground and aerial imagery,” Results in Engineering, vol. 26, no. December 2024, p. 104869, 2025, doi: 10.1016/j.rineng.2025.104869.
R. Sapkota, R. H. Cheppally, A. Sharda, and M. Karkee, “YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection,” no. September 2025, pp. 1–15, 2026, [Online]. Available: http://arxiv.org/abs/2509.25164
R. Sapkota and M. Karkee, “Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition,” vol. 26, no. 2025, pp. 1–16, 2025, [Online]. Available: http://arxiv.org/abs/2510.09653
R. Sapkota and M. Karkee, “YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation,” pp. 1–16, 2026, [Online]. Available: http://arxiv.org/abs/2602.00168
I. Systems, “Analysis of Optimal Epoch Selection for YOLO26 Model in Detecting Graves and Free Slots Using UAV Photogrammetry,” vol. 7, no. 2, pp. 329–342, 2026.
E. H. Alkhammash, “A Comparative Analysis of YOLOv9, YOLOv10, YOLOv11 for Smoke and Fire Detection,” Fire, vol. 8, no. 1, 2025, doi: 10.3390/fire8010026.
S. Prabhu and K. K. Kumar, “An Improved YOLO-Based Framework for Real-Time Fire and Smoke Detection,” vol. 21, no. 7, pp. 664–671, doi: 10.67440/ahj.vi.2034.
I. Polenakis, C. Sarantidis, I. Karydis, and M. Avlonitis, “Smoke Detection on the Edge: A Comparative Study of YOLO Algorithm Variants,” Signals, vol. 6, no. 4, 2025, doi: 10.3390/signals6040060.
R. M. Sukmosuwarno, M. Faris Fadhil Islam, R. Muhammad Raditya Rahman, G. P. Mindara, and E. P. Giri, “Fire Detection Berbasis Computer Vision Menggunakan YOLOv8 Secara Real-Time,” Jurnal ICT : Information Communication & Technology, vol. 25, no. 2, pp. 154–158, 2025, doi: 10.36054/jict-ikmi.v25i2.330.
J. Kim and G. Kim, “SA-YOLO: Stage-Aware Attention for Real-Time Fire and Smoke Detection on Edge Devices,” IEEE Access, vol. 14, no. January, pp. 42270–42284, 2026, doi: 10.1109/ACCESS.2026.3674972.
A. Adi Permana, M. Rafi Muttaqin, and M. Agus Sunandar, “Sistem Deteksi Api Secara Real Time Menggunakan Algoritma You Only Look Once (Yolo) Versi 8,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 8, no. 5, pp. 10395–10400, 2024, doi: 10.36040/jati.v8i5.10847.
A. Bayegizova et al., “Fire detection using deep learning methods,” International Journal of Electrical and Computer Engineering, vol. 14, no. 1, pp. 547–555, 2024, doi: 10.11591/ijece.v14i1.pp547-555.
C. L. Jayanth and H. T. Manjunath, “Intelligent Fire Detection with Automated Recognition and Alerting using YOLOv8 Deep Learning Method,” pp. 200–206, 2024.
M. Atta, M. Ali, T. Aly, A. T. Raslan, M. Gheith, and E. A. Amin, “Advancing Crowd Object Detection : A Review of YOLO , CNN and ViTs Hybrid Approach *,” pp. 175–221, 2024, doi: 10.4236/jilsa.2024.163011.
U. Sirisha, S. P. Praveen, P. N. Srinivasu, P. Barsocchi, and A. K. Bhoi, “Statistical Analysis of Design Aspects of Various YOLO-Based Deep Learning Models for Object Detection,” International Journal of Computational Intelligence Systems, vol. 16, no. 1, pp. 1–29, 2023, doi: 10.1007/s44196-023-00302-w.
Y. Zheng, P. Guo, X. Tian, and Y. Ye, “A forest fire identification and monitoring model based on improved YOLOv8,” Sci. Rep., vol. 15, no. 1, pp. 1–18, 2025, doi: 10.1038/s41598-025-17893-3.
V. Bhardwaj, A. Akansha, and G. R. Devi, “A Lightweight Fire Detection Framework Based on YOLOv11 for Deployment on Embedded UAV Systems UAV Systems,” pp. 0–12, 2026, doi: 10.20944/preprints202602.1002.v1.
ROSCODE [Roscoe Kerby], “Fire/Smoke Detection YOLO v9,” Kaggle. Accessed: Feb. 28, 2026. [Online]. Available: https://www.kaggle.com/datasets/roscoekerby/firesmoke-detection-yolo-v9/data
J. Wang, Y. Yao, Y. Huo, and J. Guan, “FM-Net: A New Method for Detecting Smoke and Flames,” Sensors, vol. 25, no. 17, pp. 1–20, 2025, doi: 10.3390/s25175597.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Surya Pratama Adi Putra
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
