A Study on Performance Analysis of Electric Vehicle Fire and Smoke Object Detection Based on Different Labeling Methods Using the YOLOv11 Model
Authors:
Open Access
- 31 December 2025
- journal article
- Published by Korea Institute of Fire Science and Engineering in International Journal of Fire Science and Engineering
- Vol. 39 (4) , 16-25
Abstract
This study evaluated the performance of YOLOv11 models trained to detect electric vehicle (EV) fires and smoke emission using bounding-box and instance segmentation annotations. Comprehensive experiments were conducted across all YOLOv11 variants (n, s, m, l, x) to analyze the trade-offs between speed and detection accuracy. The models were trained on a dataset consisting of 3,000 images depicting EV fires and smoke, which were annotated using Roboflow’s polygon tool under identical training conditions with consistent hardware and hyperparameters. The evaluation was based on precision, recall, and mean average precision at an intersection over union threshold of 0.50 (mAP50), as well as mAP50-95, F1-score, and inference speed in frames per second. The experimental results showed distinct advantages for each annotation method. Bounding-box models demonstrated superior inference speed, with the YOLOv11n model achieving the highest speed at 44.62 FPS. This makes these methods optimal for real-time EV fire monitoring applications. By contrast, segmentation models showed significantly higher accuracy in detecting objects with irregular boundaries, particularly smoke plumes. The YOLOv11m model with segmentation achieved optimal performance with a mAP50 of 0.7952 and an F1-score of 0.7510. The segmentation approach proved particularly effective for smoke detection, where bounding-box annotation frequently failed to accurately capture the irregular boundaries of smoke in an image, which resulted in detection failures for these critical fire indicators. These findings demonstrate that segmentation labeling is more effective in achieving accurate early detection and precise localization of EV fires and smoke emissions, despite the computational trade-off. The superior boundary definition capability of the segmentation approach is crucial for reliable smoke detection, which provides an important early warning of thermal runaway events in EV batteries. Future studies will focus on expanding the diversity of the dataset used to train the models by applying generative AI techniques such as GAN and diffusion models to further enhance detection robustness across varied fire scenarios.Keywords
Funding Information
- National Research Foundation of Korea (2021R1G1A1014385)
- Ministry of Science and ICT
This publication has 6 references indexed in Scilit:
- Ignition Point Prediction by Combustion Patterns Analysis in EV Battery FireMagazine of Fire Investigation Socity of Korea, 2025
- Legislative Improvement and Legislative Direction to Promote Reuse and Recycling of Electric Vehicle BatteriesJournal of Legislative Studies, 2025
- A Study on the Problems and Countermeasures of Electric Vehicle Fires in Underground Parking Lots: Focusing on the 4M Analysis Method2025
- Multi-Classification Using YOLOv11 and Hybrid YOLO11n-MobileNet Models: A Fire Classes Case StudyFire, 2025
- How to reduce the greenhouse gas emissions and air pollution caused by light and heavy duty vehicles with battery-electric, fuel cell-electric and catenary trucksEnvironment International, 2021
- Demand Analysis and Forecasting of Battery Electric Vehicles in KoreaJournal of the Korean Society of Supply Chain Management, 2020