UAV-based multispectral images of spring wheat

The experiments were conducted at the Agriculture Experimental located south of Brazil, from May to October in 2018. The study area contains several 2.5m x 1m rectangular parcels, referred to as plots, which hold two Brazilians wheat varieties. The genotypes used were TBIO Toruk and BRS Parrudo (48 Toruk plots and 40 Parrudo plots). Variability in the growth of the crops was created for all test areas, where each one received a varying quantity of nitrogen. Different Nitrogen (N) rates were chosen to generate crop growth variability, to evaluate the response of biomass and grain yield to N availability, which we called spatial variability. The database consists of images captured by Unmanned Aerial Vehicles (UAV) and biomass manual measurements. Two different processes were used to create this dataset. In the first, we collected the biomass to make a ground-truth. This step is done manually and destructively. Shoot dry biomass was determined at three growth stages: the stage of six fully expanded leaves, referred herein as V6, three nodes, and at flowering by the collecting of plants in an area of 0.27 m² for each plot. This was done to create a temporal variability. The plants collected were oven-dried at 65ºC until constant weight and weighed. Then the value is extrapolated for kilograms/hectare (Kg/ha). That is the BIOMASS value in the CSV file. The second process was to acquire the images at the height of 50m above ground using a camera coupled to a DJI Matrice 100 Quadcopter to obtain images with a ground sample distance (GSD) of 0.0465m. The camera mounted in the UAV was a multispectral Parrot Sequoia MicaSense (2018) for agricultural applications that is independent of the UAV systems. This multispectral camera has four independent monochrome channels (1280 x 960, 10 bits per pixel). The single grid flight plan for image acquisition was used in this work, being a common setup used by UAV flight control applications when mapping terrain used in agriculture Pix4d (2019). The frontal and lateral overlaps between images were adjusted to 80% and 60%, respectively, which is controlled by the camera itself using an internal GNSS trigger. Post-processing of the acquired images includes georeferencing and orthomosaic generation.

本实验于2018年5月至10月在巴西南部某农业试验场开展。试验区域内设有若干2.5米×1米的矩形地块（以下简称样地），共种植两个巴西小麦品种。供试基因型为TBIO Toruk与BRS Parrudo，其中Toruk样地48个，Parrudo样地40个。本研究对所有试验地块施加不同用量的氮肥，以营造作物生长的梯度差异；通过设置不同施氮量（N）梯度构建作物生长的空间变异特征，以此评估生物量与籽粒产量对氮素有效性的响应。本数据集包含由无人机（Unmanned Aerial Vehicles, UAV）采集的影像以及人工实测的生物量数据。本数据集通过两类流程构建：第一类流程为生物量地面真值（ground-truth）采集，该步骤属于人工破坏性采样。在三个生育期测定地上部干生物量：分别为六叶期（本研究中记为V6）、三节期及开花期；每个样地内采集0.27平方米区域内的植株进行测定，以此构建作物生长的时间变异梯度。采集的植株经65℃烘箱烘干至恒重后称重，再将测得值换算为千克/公顷（Kg/ha），此即为CSV文件中的BIOMASS字段值。第二类流程为无人机影像采集：搭载于DJI Matrice 100四旋翼无人机的相机在距地面50米高度作业，所得影像的地面采样距离（Ground Sample Distance, GSD）为0.0465米。该无人机搭载的相机为适用于农业场景的多光谱Parrot Sequoia MicaSense（2018款），其系统独立于无人机本体。这款多光谱相机拥有4个独立的单色通道，分辨率为1280×960，单像素位深为10比特。本研究采用单网格飞行计划开展影像采集，该方案是农业地形测绘中无人机飞行控制软件（如Pix4d 2019）的常用设置。影像间的航向重叠度与旁向重叠度分别调整为80%与60%，该参数由相机内置的GNSS触发器自动控制。采集所得影像的后处理流程包括地理配准与正射影像镶嵌生成。

搜集汇总

背景与挑战

背景概述

该数据集是一个基于无人机获取的春小麦多光谱图像集合，包含2018年在巴西南部采集的图像和生物量测量数据，涉及两个小麦品种和不同氮素处理，旨在评估作物生长变异性，适用于精准农业研究。数据集包括图像、CSV文件和地块信息，总大小813 MB，发布于2022年，采用CC BY NC 3.0许可证。