TreeLearn: A Comprehensive Deep Learning Method for Segmenting Individual Trees from Forest Point Clouds

Laser-scanned point clouds of forests make it possible to extract valuable information for forest management. To consider single trees, a forest point cloud needs to be segmented into individual tree point clouds. Existing segmentation methods are usually based on hand-crafted algorithms, such as identifying trunks and growing trees from them, and face difficulties in dense forests with overlapping tree crowns. In this study, we propose \mbox{TreeLearn}, a deep learning-based approach for semantic and instance segmentation of forest point clouds. Unlike previous methods, TreeLearn is trained on already segmented point clouds in a data-driven manner, making it less reliant on predefined features and algorithms. Additionally, we introduce a new manually segmented benchmark forest dataset containing 156 full trees, and 79 partial trees, that have been cleanly segmented by hand. This enables the evaluation of instance segmentation performance going beyond just evaluating the detection of individual trees. We trained TreeLearn on forest point clouds of 6665 trees, labeled using the Lidar360 software. An evaluation on the benchmark dataset shows that TreeLearn performs equally well or better than the algorithm used to generate its training data. Furthermore, the method's performance can be vastly improved by fine-tuning on the cleanly labeled benchmark dataset. The TreeLearn code is availabe from https://github.com/ecker-lab/TreeLearn. The data as well as trained models can be found at https://doi.org/10.25625/VPMPID.

Assessing out-of-domain generalization for robust building damage detection

An important step for limiting the negative impact of natural disasters is rapid damage assessment after a disaster occurred. For instance, building damage detection can be automated by applying computer vision techniques to satellite imagery. Such models operate in a multi-domain setting: every disaster is inherently different (new geolocation, unique circumstances), and models must be robust to a shift in distribution between disaster imagery available for training and the images of the new event. Accordingly, estimating real-world performance requires an out-of-domain (OOD) test set. However, building damage detection models have so far been evaluated mostly in the simpler yet unrealistic in-distribution (IID) test setting. Here we argue that future work should focus on the OOD regime instead. We assess OOD performance of two competitive damage detection models and find that existing state-of-the-art models show a substantial generalization gap: their performance drops when evaluated OOD on new disasters not used during training. Moreover, IID performance is not predictive of OOD performance, rendering current benchmarks uninformative about real-world performance. Code and model weights are available at https://github.com/ecker-lab/robust-bdd.