Blackberries Flower Dataset

Citation Author(s):
Christopher
Tatsch
West Virginia University
Jared
Strader
Massachusetts Institute of Technology
Nicole
Waterland
West Virginia University
Sarah
Mills
West Virginia University
Ahmed
Sidiya
West Virginia University
Mindi
Ruan
West Virginia University
Xin
Li
West Virginia University
Jason
Gross
West Virginia University
Yu
Gu
West Virginia University
Submitted by:
Christopher Tatsch
Last updated:
Wed, 03/09/2022 - 19:00
DOI:
10.21227/vyhn-9e16
Data Format:
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

This dataset consists of 1878 labeled images of flowers from blackberry trees from the specie Rubus L. subgenus Rubus Watson. These are white flowers with five petals that blossom in the spring through summer. The images were collected using an Intel RealSense D435i camera inside a greenhouse.

This images were inicially collected to support a robotic autonomous pollination project.

Instructions: 

The images size are 640x480. For each image there is a *.json annotation and a *.png mask with the same namespace. The list_of_imgs text file lists all the image names in the dataset.The image annotation consist of the points where the flower pistils are localized in the flower and a mask for the entire flower clusters in the images.The flowers images were collected two and three days after anthesis (flower opening). The images were annotated using supervisely format, and can be easily converted to other formats for using various machine learning algorithms.

Funding Agency: 
USDA NIFA Project: 2017-67022-25926 and USDA NIFA 2022-67021-36124