Urb3DCD : Urban Point Clouds Simulated Dataset for 3D Change Detection

In a context of rapid urban evolution, there is a need of surveying cities. Nowadays predictive models based on machine learning require large amount of data to be trained, hence the necessity of providing some public dataset allowing to follow up urban evolution. While most of changes occurs onto the vertical axis, there is no public change detection dataset composed of 3D point clouds and directly annotated according to the change at point level yet. With the proposed dataset, we aim to fill this gap since we believe that 3D point clouds bring some supplementary information on height that seems useful in the context of building change extraction, given that main modifications occur onto the vertical axis. Furthermore, spectral variability of a same object over time, difference of viewing angles between acquisition of 2D images, perspective and distortion effects could complicate change retrieval based on 2D data. Thus, this dataset is composed of bi-temporal pairs of point clouds annotated according to the change. Point clouds are acquired via a simulator of aerial LiDAR Survey over dense urban areas. Changes are also introduced by the simulator. The dataset is made of challenging low resolution point clouds. Training, validation and testing sets are furnished. Notice that this dataset will be extended in the future, with various point resolution, noise level, and acquisition conditions.