Workflows

DeepTrees python workflows are able to train and predict multiple deep learning models. The workflows are also able to analyze the predictions to derive tree metrics. A sample run of the workflows can be viewed on our Mage AI instance here:

The following mindmap provides an overview of the workflows for training and prediction of multiple deep learning models and the analysis workflows for deriving tree metrics from predictions.

Warning

The python workflows are currently under development and this webpage will be updated soon with links to code and documentation. We will also publish a map and a dashboard for the results of the workflows.

Tree Detection and Segmentation Models used in DeepTrees

Tree Detection

ResNet Object Detection

Weinstein, B.G., Marconi, S., Aubry‐Kientz, M., Vincent, G., Senyondo, H. and White, E.P., 2020. DeepForest: A Python package for RGB deep learning tree crown delineation. Methods in Ecology and Evolution, 11(12), pp.1743-1751.

Website Code

Tree Segmentation

UNet Segmentation

Freudenberg, M., Magdon, P. and Nölke, N., 2022. Individual tree crown delineation in high-resolution remote sensing images based on U-Net. Neural Computing and Applications, 34(24), pp.22197-22207.

Website Code