Leafy Spurge 数据集：航拍无人机图像中的真实世界杂草分类
Leafy Spurge Dataset: Real-world Weed Classification Within Aerial Drone Imagery
AI总结：
本文构建并发布含标注与无标注无人机图像的 Leafy Spurge 数据集，并基于预训练 DINOv2 视觉 Transformer 实现 0.84 测试准确率，证明杂草遥感分类可行但仍需改进。
摘要：
入侵植物物种对农业和野地的生态都有害。Euphorbia esula（即 leafy spurge，乳浆大戟）就是这样一种植物，它从东欧蔓延到北美大部分地区。当与现代计算机视觉系统结合时，无人驾驶飞行器（或称无人机）提供了追踪 leafy spurge 等问题植物扩张的手段，并提高控制这些杂草的机会。我们收集了一个关于美国蒙大拿州西部草原中 leafy spurge 存在与不存在的数据集，随后使用商用无人机对这些区域进行了航测。我们在这些数据上训练了图像分类器，其中表现最好的模型是一个预训练的 DINOv2 视觉 Transformer，在测试集上以 0.84 的准确率识别出 leafy spurge。该结果表明，leafy spurge 的分类是可处理的，但尚未得到解决。我们向机器学习社区发布这一独特的、包含有标注和无标注航拍无人机图像的数据集以供探索。提升 leafy spurge 的分类性能将使生态学、保护和遥感等领域共同受益。代码和数据可在我们的网站获取：leafy-spurge-dataset.github.io。
英文摘要：
Invasive plant species are detrimental to the ecology of both agricultural and wildland areas. Euphorbia esula, or leafy spurge, is one such plant that has spread through much of North America from Eastern Europe. When paired with contemporary computer vision systems, unmanned aerial vehicles, or drones, offer the means to track expansion of problem plants, such as leafy spurge, and improve chances of controlling these weeds. We gathered a dataset of leafy spurge presence and absence in grasslands of western Montana, USA, then surveyed these areas with a commercial drone. We trained image classifiers on these data, and our best performing model, a pre-trained DINOv2 vision transformer, identified leafy spurge with 0.84 accuracy (test set). This result indicates that classification of leafy spurge is tractable, but not solved. We release this unique dataset of labelled and unlabelled, aerial drone imagery for the machine learning community to explore. Improving classification performance of leafy spurge would benefit the fields of ecology, conservation, and remote sensing alike. Code and data are available at our website: leafy-spurge-dataset.github.io.
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。
