仅用RGB图像实现无人机野火温度像素级预测，无需热成像仪。
Seeing Heat with Color -- RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth
- 用多模态教师网络从红外数据中学到温度知识，蒸馏给单模态学生网络。
- 在FLAME 3数据集上实现像素级温度回归，精度媲美带热成像的系统。
- 适合低成本无人机火灾监测，尤其关注硬件轻量化与部署效率的团队。
使用无人机（UAV）进行高保真野火监测通常需要多模态感知——尤其是可见光（RGB）与热成像——这增加了硬件成本和功耗。本文提出SAM-TIFF，一种基于教师-学生蒸馏的新型框架，仅利用RGB输入即可实现像素级野火温度预测与分割。一个多模态教师网络在配对的RGB-热成像数据及辐射计校准的TIFF地面真值上训练，将知识蒸馏至仅输入RGB的单模态学生网络，实现无热传感器的温度推断。分割监督通过结合SAM引导的掩码生成、TOPSIS筛选，以及Canny边缘检测与Otsu阈值化流水线自动选择点提示。本方法是首个从无人机RGB数据中实现像素级温度回归的工作，在最新的FLAME 3数据集上展现出强泛化能力。该研究为无需热成像仪的轻量、低成本无人机野火监测系统奠定了基础。
原文摘要 · Abstract (English)
High-fidelity wildfire monitoring using Unmanned Aerial Vehicles (UAVs) typically requires multimodal sensing - especially RGB and thermal imagery - which increases hardware cost and power consumption. This paper introduces SAM-TIFF, a novel teacher-student distillation framework for pixel-level wildfire temperature prediction and segmentation using RGB input only. A multimodal teacher network trained on paired RGB-Thermal imagery and radiometric TIFF ground truth distills knowledge to a unimodal RGB student network, enabling thermal-sensor-free inference. Segmentation supervision is generated using a hybrid approach of segment anything (SAM)-guided mask generation, and selection via TOPSIS, along with Canny edge detection and Otsu's thresholding pipeline for automatic point prompt selection. Our method is the first to perform per-pixel temperature regression from RGB UAV data, demonstrating strong generalization on the recent FLAME 3 dataset. This work lays the foundation for lightweight, cost-effective UAV-based wildfire monitoring systems without thermal sensors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。