Affiliation:
1. Faculty of Electronics, Telecommunications and Information Technology, Gheorghe Asachi Technical University of Iasi, Bd. Carol I 11A, 700506 Iasi, Romania
Abstract
The paper introduces a new FireAndSmoke open dataset comprising over 22,000 images and 93,000 distinct instances compiled from 1200 YouTube videos and public Internet resources. The scenes include separate and combined fire and smoke scenarios and a curated set of difficult cases representing real-life circumstances when specific image patches may be erroneously detected as fire/smoke presence. The dataset has been constructed using both static pictures and video sequences, covering day/night, indoor/outdoor, urban/industrial/forest, low/high resolution, and single/multiple instance cases. A rigorous selection, preprocessing, and labeling procedure has been applied, adhering to the findability, accessibility, interoperability, and reusability specifications described in the literature. The performances of the YOLO-type family of object detectors have been compared in terms of class-wise Precision, Recall, Mean Average Precision (mAP), and speed. Experimental results indicate the recently introduced YOLO10 model as the top performer, with 89% accuracy and a mAP@50 larger than 91%.
Reference55 articles.
1. Kumar, A. (2022). Preserving life on earth. Adaptation, Ecosystem-Based, Elsevier.
2. (2024, July 02). International Association of Fire and Rescue Services. Available online: www.ctif.org/news/world-fire-statistics-report-no-29-comprehensive-analysis-fire-statistics-2022.
3. Integrating multiple factors to optimize watchtower deployment for wildfire detection;Zhang;Sci. Total Environ.,2020
4. Chagger, R., and Smith, D. (2014). The Causes of False Fire Alarms in Buildings, BRE Trust. Tech. Rep. BC2982, no. 1.
5. (2009). Statistics 2008, Duisburg Fire Brigade.