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

Citation Author(s):
de Gélis
IRISA/Univsersité Bretagne Sud
Submitted by:
Iris de Gelis
Last updated:
Tue, 06/01/2021 - 04:14
Data Format:
0 ratings - Please login to submit your rating.


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.


Urban Point Clouds simulator

We have developed a simulator to generate time series of point clouds (PCs) for urban datasets. Given a 3D model of a city, the simulator allows us to introduce random changes in the model and generates a synthetic aerial LiDAR Survey (ALS) above the city. The 3D model is in practice issued from a real city, e.g. with a Level of Detail 2 (LoD2) precision. From this model, we extract each existing building as well as the ground. By adding or removing buildings in the model, we can simulate construction or demolition of buildings. Notice that depending on area the ground is not necessarily flat. The simulator allows us to obtain as many 3D PCs over urban changed areas as needed. It could be useful especially for deep learning supervised approaches that require lots of training dates. Moreover, the created PCs are all directly annotated by the simulator according to the changes, thus no time-consuming manual annotation needs to be done with this process.

For each obtained model, the ALS simulation is performed thanks to a flight plan and ray tracing with the Visualisation ToolKit (VTK) python library.  Space between flight lines is computed in accordance to predefined parameters such as resolution, covering between swaths and scanning angle. Following this computation, a flight plan is set with a random starting position and direction of flight in order to introduce more variability between two acquisitions. Moreover, Gaussian noise can be added to simulate errors and lack of precision in LiDAR range measuring and scan direction.

Dataset Description

To conduct fair qualitative and quantitative evaluation of PC change detection techniques, we have build some datasets based on LoD2 models of the first and second districts of Lyon  (https://geo.data.gouv.fr/datasets/0731989349742867f8e659b4d70b707612bece89), France. For each simulation, buildings have been added or removed to introduce changes in the model and to generate a large number of pairs of PCs. We also consider various initial states across simulations, and randomly update the set of buildings from the first date through random addition or deletion of  buildings to create the second landscape. In addition, flight starting position and direction are always set randomly. As a consequence, the acquisition patterns will not be the same between generated PCs, thus each acquisition may not have exactly the same visible or hidden parts.

This first version of the dataset is composed of point clouds at a challenging low resolution of around 0.5 points/meter².

Technical details

All PCs are available at PLY format. Each train, val, test folder contains sub-folders containing pairs of PCs : pointCloud0.ply and pointCloud1.ply for both first and second dates.

Each ply file contain the coordinates X Y Z of each points and the label:

  • 0 for unchanged points
  • 1 for points on a new building
  • 2 for for points on a destruction.

The label is given in a scalar field named label_ch. Notice that the first PC (pointCloud0.ply) has a label field even if it is set at 0 for every points because change are set in comparison to previous date.


If you use this dataset for your work, please use the following citation:

@inproceedings{degelis2021,  title={Benchmarking change detection in urban 3D point clouds},  author={de G\'elis, I. and Lef\`evre, S. and Corpetti, T. and Ristorcelli, T. and Th\'enoz, C. and Lassalle, P.},  booktitle={IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},  year={2021}}