Learning Digital Terrain Models from Point Clouds: ALS2DTM Dataset and Rasterization-based GAN
This work addresses a domain-specific problem in geospatial analysis by providing a dataset and method for DTM extraction, which is incremental as it builds on existing techniques with new data and a baseline approach.
The paper tackles the challenge of extracting digital terrain models (DTMs) from airborne laser scanning point clouds by introducing a large-scale annotated dataset and a baseline method called DeepTerRa, achieving sub-metric error levels compared to existing methods.
Despite the popularity of deep neural networks in various domains, the extraction of digital terrain models (DTMs) from airborne laser scanning (ALS) point clouds is still challenging. This might be due to the lack of dedicated large-scale annotated dataset and the data-structure discrepancy between point clouds and DTMs. To promote data-driven DTM extraction, this paper collects from open sources a large-scale dataset of ALS point clouds and corresponding DTMs with various urban, forested, and mountainous scenes. A baseline method is proposed as the first attempt to train a Deep neural network to extract digital Terrain models directly from ALS point clouds via Rasterization techniques, coined DeepTerRa. Extensive studies with well-established methods are performed to benchmark the dataset and analyze the challenges in learning to extract DTM from point clouds. The experimental results show the interest of the agnostic data-driven approach, with sub-metric error level compared to methods designed for DTM extraction. The data and source code is provided at https://lhoangan.github.io/deepterra/ for reproducibility and further similar research.