arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02465cs.CVcs.AI

基于深度学习的泥炭地火灾检测：使用迁移学习

Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptation

Department of Electrical and Computer Engineering University of Illinois Chicago（电气与计算机工程系伊利诺伊大学芝加哥分校）；Fire and Rescue Department of Malaysia（马来西亚消防与救援部门）；Dept. of Chemical and Environmental Engineering Faculty of Engineering Universiti Putra Malaysia（化学与环境工程系乌拉尔大学马来西亚分校）；International Tropical Forestry Programme Faculty of Tropical Forestry Universiti Malaysia Sabah（国际热带林业计划热带林业系马来西亚沙巴大学）；USDA Forest Service Pacific Wildland Fire Sciences Laboratory（美国农业部森林服务局太平洋野火科学实验室）

Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir, Dayang Nur Sakinah Musa, Erdem Koyuncu, Adam J. Watts, Ahmet Enis Cetin

备注：
Accepted as a journal in Signal, Image and Video Processing (SVIP) Springer Journal
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于迁移学习的深度学习方法，用于检测泥炭地火灾，通过预训练模型和数据集微调提升检测准确性和鲁棒性。

摘要：

近年来，基于机器学习（ML）的野火检测方法已得到发展，主要使用深度学习（DL）模型在大量野火图像和视频上进行训练。然而，泥炭地火灾具有独特的视觉和物理特征——如缓慢燃烧、低火焰强度、持续烟雾和地下燃烧——这限制了传统野火检测器在开放火焰森林火灾上的有效性。在本工作中，我们提出了一种基于迁移学习的泥炭地火灾检测方法，该方法利用从一般野火图像中学习到的知识，并将其适应到泥炭地火灾领域。我们使用预训练权重初始化一个基于深度学习的泥炭地火灾检测器，并随后使用由马来西亚泥炭地图像和视频组成的数据集对网络进行微调。这种策略在标签有限的泥炭地火灾数据情况下也能实现有效的学习。实验结果表明，与从头训练相比，迁移学习在低对比度烟雾、部分遮挡和光照变化等挑战性条件下显著提高了检测准确性和鲁棒性。所提出的方法为早期泥炭地火灾检测提供了实用且可扩展的解决方案，并有潜力支持火灾预防和环境保护的实时监控系统。

英文摘要：

Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video datasets. However, peatland fires exhibit distinct characteristics, including smoldering combustion, low flame intensity, persistent smoke, and subsurface burning, limiting the effectiveness of conventional wildfire detectors. To address these challenges, we propose an efficient deep learning framework for peatland fire detection based on a Walsh--Hadamard Transform enhanced ResNet-50 (WHT-ResNet-50), which improves feature representation while reducing model complexity. To enable efficient deployment, the training-time architecture is structurally reparameterized into an equivalent inference model without sacrificing detection performance. Furthermore, the proposed framework leverages wildfire-to-peatland domain adaptation through transfer learning and introduces a mixed-domain training strategy that produces a unified detector capable of recognizing both wildfire and peatland fire events. Experimental results demonstrate that transfer learning substantially improves peatland fire detection under limited-data conditions, while the proposed WHT-ResNet-50 achieves higher accuracy and F1-score than conventional architectures with fewer parameters. The structurally reparameterized model further reduces inference cost while preserving detection accuracy. Video-based evaluation demonstrates robust performance with low false alarm rates, achieving a 100\% event detection rate across all positive test videos. Overall, the proposed framework provides an accurate, efficient, and practical solution for early peatland fire detection.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑