Bramble Flower Detection and Classification Dataset for Precision Pollination
- Citation Author(s):
-
Madhav Rijal (West Virginia University)Trevor Smith (West Virginia University)Christopher Tatsch (West Virginia University)Jared Beard (West Virginia University)Andy Chu (West Virginia University)R. Michael Butts (West Virginia University)Nicole Waterland (West Virginia University)Jason Gross (West Virginia University)Yu Gu (West Virginia University)
- Submitted by:
- Madhav Rijal
- Last updated:
- DOI:
- 10.21227/b58f-jt53
497 views
- Categories:
- Keywords:
Abstract
This dataset contains both the artificial and real flower images of bramble flowers. The real images were taken with a realsense D435 camera inside the West Virginia University greenhouse. All the flowers are annotated in YOLO format with bounding box and class name. The trained weights after training also have been provided. They can be used with the python script provided to detect the bramble flowers. Also the classifier can classify whether the flowers center is visible or hidden which will be helpful in precision pollination projects. Images are also augmented to make the task robust in various environmental conditions.
Instructions:
This contains two folder. One is for the detection of Bramble flowers and another is the classification of flower to find weather their center is visible or hidden.
The detection datset includes 527 images out of which 450 images are for training set(86%),57 are validation set(10%) and 20 are test set(4%).
The classification dataset includes 763 images of bramble flowers which were detected by detection algorithm. Out of them 668 images are for training(88%), 63 images are validation set (8%)and 32 images are test set(4%).
Both the artificial and real Bramble-flower are annotated in YOLOv8 format using roboflow software.
The python code for running the detection and classification is provided. The trained weights for yolov8 is provided for the dataset.
In reply to I intend to examine the by Fatma Ben Lakhdhar
y