Segmentation of sandplain lupin weeds from morphologically similar narrow-leafed lupins in the field

Dataset for weed detection used in the paper "Segmentation of sandplain lupin weeds from morphologically similar narrow-leafed lupins in the field". <br> The scripts developed are available on GitHub at mdanilevicz/WeedDetectionML. <br> This repository contains five datasets collected in the field by drone or smartphone in Western Australia, Australia. The images for <strong>field-1, field-2, grow-1</strong> and <strong>grow-2</strong> datasets were collected using the DJI Phantom 4 unoccupied aerial vehicle (UAV) RGB camera. The images were collected between 12 and 2 PM under overcast or clear sky conditions. The details for the image collection can be seen in Table 3. The images were collected with 75% side overlap and 80% front overlap, with five ground control points distributed across the field to increase GPS accuracy. Additionally, 217 images with 4879 sandplain lupins labelled among narrow-leafed lupins were downloaded from the Weed-AI database and named <strong>ext-1 </strong>dataset. <br> In this repository you will find the RGB images, plant-soil segmentation mask obtained using CIVE vegetation index and weed-crop-soil segmentation mask. <br> Detailed methods fro dataset generation is available on the paper, and github repositories. <br> <br>

本数据集用于论文《田间形态相似窄叶羽扇豆与沙原羽扇豆杂草的分割》中的杂草检测研究。
所开发的配套脚本已托管于GitHub平台的mdanilevicz/WeedDetectionML仓库。
该仓库包含澳大利亚西澳大利亚州通过无人机或智能手机野外采集的五组数据集。其中field-1、field-2、grow-1及grow-2数据集的图像均采用大疆精灵4（DJI Phantom 4）无人飞行器（UAV）的RGB相机采集。图像采集时段为正午12时至下午2时，天气条件为阴天或晴朗。图像采集的详细信息详见表3。本次采集采用75%的旁向重叠率与80%的航向重叠率，并在田间布设5个地面控制点以提升GPS定位精度。
此外，从Weed-AI数据库中下载了217张图像，其中包含标注于窄叶羽扇豆种群中的4879株沙原羽扇豆，该数据集被命名为ext-1。
本仓库包含RGB图像、基于CIVE植被指数得到的植株-土壤分割掩码，以及杂草-作物-土壤分割掩码。
数据集生成的详细方法可参阅该论文及GitHub仓库中的相关内容。