Scholarlink

Abstract <p>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 at evaluating the efficiency of these approaches in terms of execution time and fire detection accuracy based on RMSE, IoU, Dice, and MAPE metrics. The 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 and Dice 0.1588–0.5026). The U-Net neural network demonstrates higher fire segmentation accuracy (IoU up to 0.6015 and 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%). The 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 development of hybrid approaches.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Experimental Study of HSV Threshold Method and U-Net Neural Network in Fire Recognition Task

  • 期刊论文

  • 发表日期：

    2025年12月1日

查看全文
  • M. V. Bobyr,
  • N. A. Milostnaya,
  • B. A. Bondarenko,
  • M. M. Bobyr

摘要

Abstract

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 at evaluating the efficiency of these approaches in terms of execution time and fire detection accuracy based on RMSE, IoU, Dice, and MAPE metrics. The 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 and Dice 0.1588–0.5026). The U-Net neural network demonstrates higher fire segmentation accuracy (IoU up to 0.6015 and 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%). The 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 development of hybrid approaches.