使用由大型教师模型训练的实时分割在无人机上检测野火
Detecting Wildfires on UAVs with Real-time Segmentation Trained by Larger Teacher Models
AI总结：
本研究提出利用零样本基础模型监督和边界框标签训练小型分割模型，在无人机上实现野火烟雾实时分割，准确率达63.3% mIoU且帧率约25 fps。
摘要：
早期发现野火对于防止导致广泛环境、结构和社会破坏的大规模火灾至关重要。无人飞行器（UAV）能有效覆盖广阔偏远地区，快速部署所需基础设施极少，配备小型相机和计算机即可实现自主实时检测。然而在偏远地区，由于缺乏高带宽移动网络，检测方法仅限于机载计算。为实现基于相机的准确定位，对检测到的烟雾进行分割至关重要，但基于深度学习的野火烟雾分割训练数据有限。本研究展示了如何仅使用边界框标签，利用零样本基础模型监督来训练小型专用分割模型。该方法的优势在于仅需较易获取的边界框标签，且只需对较小的学生网络进行训练。所提方法在人工标注的多样化野火数据集上达到63.3% mIoU。该模型可在搭载NVIDIA Jetson Orin NX计算机的UAV上以~25 fps实时运行，并在现实森林燃烧事件中可靠识别烟雾。代码可在：https://gitlab.com/fgi_nls/public/wildfire-real-time-segmentation 获取。
英文摘要：
Early detection of wildfires is essential to prevent large-scale fires resulting in extensive environmental, structural, and societal damage. Uncrewed aerial vehicles (UAVs) can cover large remote areas effectively with quick deployment requiring minimal infrastructure and equipping them with small cameras and computers enables autonomous real-time detection. In remote areas, however, detection methods are limited to onboard computation due to the lack of high-bandwidth mobile networks. For accurate camera-based localisation, segmentation of the detected smoke is essential but training data for deep learning-based wildfire smoke segmentation is limited. This study shows how small specialised segmentation models can be trained using only bounding box labels, leveraging zero-shot foundation model supervision. The method offers the advantages of needing only fairly easily obtainable bounding box labels and requiring training solely for the smaller student network. The proposed method achieved 63.3% mIoU on a manually annotated and diverse wildfire dataset. The used model can perform in real-time at ~25 fps with a UAV-carried NVIDIA Jetson Orin NX computer while reliably recognising smoke, as demonstrated at real-world forest burning events. Code is available at: https://gitlab.com/fgi_nls/public/wildfire-real-time-segmentation
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。
