Grape image database

The GrapeCS-ML database consists of images of grape varieties at different stages of development together with the corresponding ground truth data (e.g., pH and Brix) obtained from chemical analysis. One of the objectives of this database is to motivate computer vision and machine learning researchers to develop practical solutions for deployment in smart vineyards. The database consists of images of bunches in three Australian vineyards and contains different datasets for evaluation. The database consists of five datasets for 15 grape varieties taken at several stages of development and includes size and/or Macbeth colour references. Altogether, the database contains a total of 2078 images, which is downloadable as a zip file.
Set 1: Merlot bunches taken in seven rounds from the period Jan. to Apr. 2017
Set 2: Designed for research on berry and bunch volume and colour as the grapes mature, featuring Merlot, Cabernet Sauvignon, Saint Macaire, Flame Seedless, Viognier, Ruby Seedless, Riesling, Muscat Hamburg, Purple Cornichon, Sultana, Sauvignon Blanc and Chardonnay.
Set 3: Subsets for two varieties (Cabernet Sauvignon and Shiraz) taken at dates close to maturity.
Set 4: Subsets of images for two varieties (Pinot Noir and Merlot) taken at dates close to maturity, with the focus on the colour changes with the onset of ripening.
Set 5: Sauvignon Blanc bunches taken on three different dates. Each image also contains a hand-segmented region defining the boundaries of the grape bunch to serve as the ground truth for evaluating computer vision techniques such as image segmentation.

葡萄CS-ML (GrapeCS-ML) 数据集收录了不同生长阶段的葡萄品种图像，以及通过化学分析得到的对应真值标签数据（如pH值与白利糖度（Brix））。该数据集的设计目标之一是推动计算机视觉与机器学习领域研究者开发可部署于智慧葡萄园的实用解决方案。本数据集的图像采集自澳大利亚三座葡萄园的葡萄果串，包含多组用于评估的子数据集。本数据集包含针对15个葡萄品种、多生长阶段采集的五组子数据集，同时配备尺寸参考物及/或麦克贝斯（Macbeth）色卡。该数据集总计包含2078张图像，可通过压缩包（zip file）下载。
数据集1：2017年1月至4月期间分7次采集的梅洛（Merlot）葡萄果串图像。
数据集2：用于研究葡萄浆果与果串在成熟过程中的体积、颜色变化，涵盖梅洛、赤霞珠（Cabernet Sauvignon）、圣马凯尔（Saint Macaire）、火焰无核（Flame Seedless）、维欧尼（Viognier）、红宝石无核（Ruby Seedless）、雷司令（Riesling）、汉堡麝香（Muscat Hamburg）、紫科尼雄（Purple Cornichon）、苏丹娜（Sultana）、长相思（Sauvignon Blanc）以及霞多丽（Chardonnay）。
数据集3：包含两个葡萄品种（赤霞珠与设拉子（Shiraz））的子数据集，采集时间接近葡萄成熟期。
数据集4：包含两个葡萄品种（黑皮诺（Pinot Noir）与梅洛）的图像子数据集，采集时间接近葡萄成熟期，重点关注葡萄成熟启动阶段的颜色变化。
数据集5：分三次不同日期采集的长相思（Sauvignon Blanc）葡萄果串图像。每张图像均附带人工标注的葡萄果串边界分割区域，可作为图像分割等计算机视觉技术评估的真值标签。