PNNL

Abstract

Cataloguing and classifying trees in the urban environment is a crucial step in urban and environmental planning, however manual collection and maintenance of this data is expensive and time-consuming. Although algorithmic approaches that rely on remote sensing data have been developed for tree detection in forests, they generally struggle in the more varied urban environment. This work proposes a novel end-to-end deep learning method for the detection of trees in the urban environment from remote sensing data. Specifically, we develop and train a novel PointNet-based neural network architecture to predict tree locations directly from LiDAR data augmented with multi-spectral imagery. We compare this model to a number of high-performing baselines on a large and varied dataset in the Southern California region, and find that our best model outperforms all baselines with a 75.5% F-score and 2.28 meter RMSE, while being highly efficient. We then analyze and compare the sources of errors, and how these reveal the strengths and weaknesses of each approach.