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.
|Date made available||2018|
|Publisher||Charles Sturt University|
|Temporal coverage||Feb 2017 - Apr 2017|
|Date of data production||Feb 2017 - Apr 2017|