Learning Image-based Tree Crown Segmentation from Enhanced Lidar-based Pseudo-labels
This provides a cost-effective solution for urban tree inventory and forest health monitoring by eliminating manual annotation needs, though it is incremental as it builds on existing pseudo-label and segmentation methods.
The study tackled the problem of automatically segmenting individual tree crowns in aerial imagery by training deep learning models using enhanced pseudo-labels from aerial laser scanning data, resulting in models that outperform general domain models on this task.
Mapping individual tree crowns is essential for tasks such as maintaining urban tree inventories and monitoring forest health, which help us understand and care for our environment. However, automatically separating the crowns from each other in aerial imagery is challenging due to factors such as the texture and partial tree crown overlaps. In this study, we present a method to train deep learning models that segment and separate individual trees from RGB and multispectral images, using pseudo-labels derived from aerial laser scanning (ALS) data. Our study shows that the ALS-derived pseudo-labels can be enhanced using a zero-shot instance segmentation model, Segment Anything Model 2 (SAM 2). Our method offers a way to obtain domain-specific training annotations for optical image-based models without any manual annotation cost, leading to segmentation models which outperform any available models which have been targeted for general domain deployment on the same task.