Grapevine Dataset for plant organ segmentation

This is a dataset for Grapevine segmentation for the purposes of winter pruning, created in a joint work between Istituto Italiano di Tecnologia and Università Cattolica del Sacro Cuore, as part of the Vinum project. The work was also cofounded by Italian Ministry of University and Research PRIN 20172HHNK5 Project, under the supervision of Matteo Gatti, Claudio Semini and Darwin Caldwell.

The images were captured in the simulated grapevine garden in Università Cattolica, located in Piacenza, Italy, and it is split in two parts, following agronomic trials being run on the university. The first part is a group of seven specimen that is the Control group, and the second group of eight specimens is being performed shoot thinning.

Each plant has around 5 spurs, and the photos are taken from both sides of the grapevine specimen, meaning that there is one picture where the plant grows from left to right, and the other side where the plant grows from right to left. The resolution of the images is 4608x3456, and we have a total of 149 images. 

It is annotated using the COCO Segmentation format,  and some of the statistics of the dataset such as the number of annotations and number of images can be seen next.

Control Complex

• Total
  • Images: 69
  • Annotated Images: 69
  • Annotations: 1838
  • Categories: 5
• Annotations Per Category
  • Main Cordon: 79
  • Cane: 440
  • Node: 1100
  • Arm: 103
  • Spur: 116
• Annotated Images Per Category
  • Main Cordon: 69
  • Cane: 69
  • Node: 69
  • Arm: 62
  • Spur: 68

Shoot Thining Simple

• Total
  • Images: 79
  • Annotated Images: 79
  • Annotations: 1635
  • Categories: 5
• Annotations Per Category
  • Main Cordon: 84
  • Cane: 341
  • Node: 912
  • Arm: 154
  • Spur: 144
• Annotated Images Per Category
  • Main Cordon: 79
  • Cane: 79
  • Node: 79
  • Arm: 79
  • Spur: 77