Development of Semantic Maps of Vegetation Cover from UAV Images to Support Planning and Management in Fine-Grained Fire-Prone Landscapes

In Mediterranean landscapes, the encroachment of pyrophytic shrubs is a driver of more frequent and larger wildfires. The high-resolution mapping of vegetation cover is essential for sustainable land planning and the management for wildfire prevention. Here, we propose methods to simplify and automate the segmentation of shrub cover in high-resolution RGB images acquired by UAVs. The main contribution is a systematic exploration of the best practices to train a convolutional neural network (CNN) with a segmentation network architecture (U-Net) to detect shrubs in heterogeneous landscapes. Several semantic segmentation models were trained and tested in partitions of the provided data with alternative methods of data augmentation, patch cropping, rescaling and hyperparameter tuning (the number of filters, dropout rate and batch size). The most effective practices were data augmentation, patch cropping and rescaling. The developed classification model achieved an average F1 score of 0.72 on three separate test datasets even though it was trained on a relatively small training dataset. This study demonstrates the ability of state-of-the-art CNNs to map fine-grained land cover patterns from RGB remote sensing data. Because model performance is affected by the quality of data and labeling, an optimal selection of pre-processing practices is a requisite to improve the results.

Automated summary

This study proposes a method for segmenting shrub cover in high-resolution UAV images by exploring the best practices to train a convolutional neural network. Data augmentation, patch cropping, and rescaling were identified as the most effective practices. Despite being trained on a relatively small dataset, the developed classification model achieved a high average F1 score on separate test datasets.