用颜色看见热量——基于SAM引导的多模态蒸馏与辐射测量地面真值，仅用RGB进行野火温度推断
Seeing Heat with Color -- RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth
AI总结：
本文提出SAM-TIFF教师-学生蒸馏框架，首次实现仅用RGB无人机影像进行像素级野火温度回归与分割，并在FLAME 3数据集上验证了泛化性能，为低成本无热传感器野火监测奠定基础。
摘要：
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RGB和热红外影像——这会增加硬件成本和功耗。本文提出SAM-TIFF，一种新颖的教师-学生蒸馏框架，用于仅使用RGB输入进行像素级野火温度预测和分割。一个在成对RGB-热红外影像和辐射测量TIFF地面真值上训练的多模态教师网络将知识蒸馏到单模态RGB学生网络，从而实现无热传感器推理。分割监督通过一种混合方法生成，该方法结合了Segment Anything（SAM）引导的掩码生成、通过TOPSIS进行的选择，以及用于自动点提示选择的Canny边缘检测和Otsu阈值处理流程。我们的方法是首个从RGB无人机数据中进行逐像素温度回归的方法，在最近的FLAME 3数据集上展现出强大的泛化能力。这项工作为无需热传感器的轻量级、高成本效益的无人机野火监测系统奠定了基础。
英文摘要：
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.
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。
