Cherry Tree Disease Detection Dataset

1. Introduction This cherry tree disease detection dataset is a multimodal, multi-angle dataset which was constructed for monitoring the growth of cherry trees, including stress analysis and prediction. An orchard of cherry trees is considered in the area of Western Macedonia, where 577 cherry trees were recorded in a full crop season starting from Jul. 2021 to Jul. 2022. The dataset includes a) aerial / Unmanned Aerial Vehicle (UAV) images, b) ground RGB images/photos, and c) ground multispectral images/photos. Two agronomist experts annotated the dataset by identifying a stress, which in this case is a common disease in cherry trees known as Armillaria [1][2]. 2. Citation Please cite the following papers when using this dataset: C. Chaschatzis, C. Karaiskou, E. Mouratidis, E. Karagiannis, and P. Sarigiannidis, “Detection and Characterization of Stressed Sweet Cherry Tissues Using Machine Learning”, Drones, vol. 6, no. 1, 2022. P. Radoglou-Grammatikis, P. Sarigiannidis, T. Lagkas, & I. Moscholios, “A compilation of UAV applications for precision agriculture,” Computer Networks, vol. 172, no. 107148, 2020. A. Lytos, T. Lagkas, P. Sarigiannidis, M. Zervakis, & G. Livanos, “Towards smart farming: Systems, frameworks and exploitation of multiple sources,” Computer Networks, vol. 172, no. 107147, 2020. 3. Cherry tree mapping In this dataset, an orchard of cherry trees is considered in the area of Western Macedonia, where 577 cherry trees were recorded in a full crop season starting from Jul. 2021 to Jul. 2022. The tree mapping within the orchard is depicted in Fig. 1. (please refer to the ReadMe file), where each circle represents a cherry tree. Labels on the circles (green, red etc) will be elaborated in the following Sections. The five time periods, where the orchard was recorded are: 8th of Jul. 2021, 16th of Sep. 2021, 3rd of Nov. 2021, 26th of May 2022, and 13th of Jul. 2022, providing data to a full year of life cycle. 4. Dataset Modalities The dataset includes a) aerial / Unmanned Aerial Vehicle (UAV) images, b) ground RGB images/photos, and c) ground multispectral images/photos. Two agronomist experts annotated the dataset by identifying a stress, which in this case is a common disease in cherry trees known as Armillaria [1][2]. In particular, the following modalities are featured in the dataset: Ground RGB images Ground multispectral images UAV/Aerial images (RGB, multispectral, and NDVI). These modalities represent the cherry tree cultivation in many levels. Each modality describes the same object (cherry tree) within the dataset, i.e., for each tree within. For example, Fig. 2 (please refer to the ReadMe file) show RGB images, Fig. 3 (please refer to the ReadMe file) illustrates multispectral images, and Fig. 4 (please refer to the ReadMe file) provides UAV images. All images show the same cherry trees under three (RGB, multispectral, and UAV) aspects. 5. Dataset Collection & Annotation This dataset was annotated by two agronomist experts in terms of disease stage (Armillaria). In particular, they annotated each cherry tree, one by one, in four levels of disease stage: Healthy: the cherry tree is completely healthy; Stage1: Armillaria is present in light form in the cherry tree; Stage2: Armillaria is present in advanced form; Stage3: the cherry tree is killed due to Armillaria. The annotation process was considered by each one of the underlying modalities (RGB, multispectral and UAV/aerial). 5.1 Image Collection The image collection is depicted in the following image (please refer to the ReadMe file) in terms of the three modalities (aerial / Unmanned Aerial Vehicle (UAV) images, ground RGB images/photos, and ground multispectral images/photos). 5.2 Dataset Overview The dataset overview is depicted in Table 1 (please refer to the ReadMe file). 6. Structure and Format 6.1 Dataset Structure The provided dataset has the following structure (please refer to the ReadMe file). 6.2 Guide to edit the *.tif files The Aerial/UAV images contain images obtained from the UAV camera in the .tif format. To open these images, you will need the QGIS or other relevant program, or load them by using the corresponding python libraries. Please follow the steps below: Open QGIS Locate the browser window in QGIS Navigate to the folder that contains the images and select all the images in the layer. Once you have selected the images, select Add Layer to Project, and the selected image will be added to your map. For accessing the Image data with the OpenCV python library the following code example is provided (please refer to the ReadMe file). 7. Acknowledgment This work was co‐financed by the European Regional Development Fund of the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH – CREATE – INNOVATE (project code: Τ1EDK-04759). This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreements No. 957406 (TERMINET). References [1] Devkota, P.; Iezzoni, A.; Gasic, K.; Reighard, G.; Hammerschmidt, R. Evaluation of the susceptibility of Prunus rootstock genotypes to Armillaria and Desarmillaria species. Eur. J. Plant Pathol. 2020, 158, 177–193. [2] Devkota, P.; Hammerschmidt, R. “The infection process of Armillaria mellea and Armillaria solidipes”. Physiol. Mol. Plant Pathol. 2020, 112, 101543.

1. 引言 本樱桃树病害检测数据集为多模态多角度数据集，旨在支撑樱桃树生长监测工作，涵盖胁迫分析与长势预测两项核心任务。研究区域选定马其顿西部的一处樱桃园，在2021年7月至2022年7月的完整作物生长季内，共完成577株樱桃树的记录与标注。本数据集包含三类数据：a) 航空/无人机（Unmanned Aerial Vehicle, UAV）影像；b) 地面RGB图像/照片；c) 地面多光谱图像/照片。两名农学家专家通过识别樱桃树常见胁迫病害——蜜环菌（Armillaria）病害，完成了本数据集的标注工作[1][2]。
2. 引用说明 若使用本数据集，请引用以下学术论文：
C. Chaschatzis, C. Karaiskou, E. Mouratidis, E. Karagiannis, P. Sarigiannidis. “Detection and Characterization of Stressed Sweet Cherry Tissues Using Machine Learning”，Drones, 第6卷第1期, 2022.
P. Radoglou-Grammatikis, P. Sarigiannidis, T. Lagkas, I. Moscholios. “A compilation of UAV applications for precision agriculture”，Computer Networks, 第172卷, 第107148号, 2020.
A. Lytos, T. Lagkas, P. Sarigiannidis, M. Zervakis, G. Livanos. “Towards smart farming: Systems, frameworks and exploitation of multiple sources”，Computer Networks, 第172卷, 第107147号, 2020.
3. 樱桃树映射 本数据集的研究区域为马其顿西部的一处樱桃园，在2021年7月至2022年7月的完整作物生长季内共记录577株樱桃树。果园内的樱桃树空间分布如图1所示（详见ReadMe文件），图中每个圆形代表一株樱桃树，圆形上的标签（绿色、红色等）将在后续章节中详细说明。本次数据采集共覆盖5个时间节点：2021年7月8日、2021年9月16日、2021年11月3日、2022年5月26日以及2022年7月13日，完整覆盖樱桃树一年的生长周期。
4. 数据集模态 本数据集包含三类数据：a) 航空/无人机（UAV）影像；b) 地面RGB图像/照片；c) 地面多光谱图像/照片。两名农学家专家已针对蜜环菌病害完成数据集标注[1][2]。具体而言，本数据集涵盖以下模态类型：
- 地面RGB图像
- 地面多光谱图像
- 无人机/航空影像（包含RGB、多光谱以及归一化差异植被指数（Normalized Difference Vegetation Index, NDVI）三类数据）
上述模态从多个维度表征樱桃树的种植状态，数据集中的每一类模态均对应同一研究对象——樱桃树，即数据集中的每一株樱桃树均拥有多模态对应数据。例如，图2（详见ReadMe文件）展示了RGB图像，图3（详见ReadMe文件）展示了多光谱图像，图4（详见ReadMe文件）展示了无人机影像。所有影像均从三个维度（RGB、多光谱、无人机航拍）呈现同一组樱桃树。
5. 数据集采集与标注 本数据集由两名农学家专家针对蜜环菌病害的发病等级完成标注。具体而言，专家们逐一对每株樱桃树的病害等级划分为四级：
- 健康：樱桃树完全无病害；
- 等级1：樱桃树感染轻度蜜环菌病害；
- 等级2：樱桃树感染重度蜜环菌病害；
- 等级3：樱桃树因感染蜜环菌病害死亡。
本次标注过程综合利用了所有三类模态数据（RGB、多光谱以及无人机/航空影像）。
5.1 图像采集 图像采集的流程如图所示（详见ReadMe文件），涵盖三类模态数据：航空/无人机（UAV）影像、地面RGB图像/照片以及地面多光谱图像/照片。
5.2 数据集概览 数据集的整体概况如表1所示（详见ReadMe文件）。
6. 结构与格式
6.1 数据集结构 本数据集的具体结构详见ReadMe文件。
6.2 *.tif文件编辑指南 无人机/航空影像采用.tif格式存储。若需打开此类影像，可使用QGIS或其他相关专业软件，或通过对应的Python库加载。具体操作步骤如下：
1. 打开QGIS软件
2. 定位QGIS中的浏览器窗口
3. 导航至存储影像的文件夹，选中所有待添加的影像文件
4. 选中影像后，选择“添加图层至项目”，即可将所选影像添加至地图中。
若需通过OpenCV Python库读取影像数据，可参考以下代码示例（详见ReadMe文件）。
7. 致谢 本研究由欧盟区域发展基金与希腊国家基金通过“竞争力、创业与创新运营计划”共同资助，对应资助号召为“研究–创造–创新（RESEARCH – CREATE – INNOVATE）”，项目编号为Τ1EDK-04759。本项目同时获得欧盟地平线2020研究与创新计划资助，资助协议编号为957406（TERMINET项目）。
参考文献
[1] Devkota, P.; Iezzoni, A.; Gasic, K.; Reighard, G.; Hammerschmidt, R. Evaluation of the susceptibility of Prunus rootstock genotypes to Armillaria and Desarmillaria species. Eur. J. Plant Pathol. 2020, 158, 177–193.
[2] Devkota, P.; Hammerschmidt, R. “The infection process of Armillaria mellea and Armillaria solidipes”. Physiol. Mol. Plant Pathol. 2020, 112, 101543.

搜集汇总

背景与挑战

背景概述

该数据集是一个多模态、多角度的樱桃树病害检测数据集，包含577棵樱桃树在一个完整生长季节（2021年7月至2022年7月）的数据。数据集包括地面RGB图像、地面多光谱图像和无人机航拍图像，并由专家标注了Armillaria病害的四个阶段（健康、初期、中期和死亡）。