Blueberry Row Detection
Deep learning algorithm for segmenting blueberry rows within orchards using UAV multispectral images.
This work has been carried out in the scope of the H2020 FlexiGroBots project, which has been funded by the European Commission in the scope of its H2020 programme (contract number 101017111, https://flexigrobots-h2020.eu/).
Provided solution approach comprises of 3 docker components with the following functionalities:
1. Downloading UAV images from minIO data storage to the local volume.
2. Training deep learning models for row segmentation.
3. Uploading trained model to minIO.
The docker containers can be obtained by the following docker commands, respectively:
1. docker pull ghcr.io/flexigrobots-h2020/training_download_component:latest
2. docker pull ghcr.io/flexigrobots-h2020/blueberry_rebuild_test1:latest
3. docker pull ghcr.io/flexigrobots-h2020/rebuild_postprocessing_component:latest
All components have been developed and tested on the Kubeflow AI platform.