Mobile Laser Scans

TUM-FAÇADE

MLS point clouds with facade-level labels (i.e., windows, doors, balconies, moldings, etc.)
33 annotated facades and 8 non-annotated for further benchmark extension or testing
~333 mln annotated points
in local and global (i.e., UTM) coordinate reference system (if struggling with the height transformation (opens in a new tab) - apply 45.66 m vertical offset)
file names point to the official CityGML LoD2 building models of Bavaria (e.g., DEBY_LOD2_4959462 -> gml_id=DEBY_LOD2_4959462) [visualisation (opens in a new tab)]
settings file for adding your own data
more info (opens in a new tab)

The test dataset TUM MLS 2016 was acquired by mobile laser scanning (MLS) using a van (testbed MODISSA) from the Fraunhofer Institute of Optronics, System Technologies, and Image Exploitation (IOSB) on April 18th, 2016.
Two Velodyne HDL-64E laser scanners were mounted at an angle of 35 degrees on the front roof of the vehicle (van).
The point cloud was acquired through more than 8000 scans (rotations of the scanner head) from each of the two laser scanners.
A rendered visualization of parts of the data and their acquisition is shown in a video clip, where each point is gray-value coded according to the echo amplitude measured by the laser scanners.
Direct georeferencing was performed using an Applanix POS LV inertial navigation system.
The dataset includes the coordinates of measured 3D points and the respective sensor positions.
The dataset contains 1,735,045,976 3D points in 17,756 .pcd files (15 minutes) and requires 62 GB of storage.
Dataset details can be found here: [http://s.fhg.de/mls1 (opens in a new tab)].

In 2018, Fraunhofer IOSB acquired mobile laser scanning (MLS) data at the test site "TUM City Campus".
More than 10,500 scans (rotations of the scanner head) were conducted using two Velodyne HDL-64E laser scanners.
The dataset contains over 2 billion 3D points in 21,170 .pcd files (17 minutes) and requires 73 GB of storage.
A basic fine-registration was performed, including loop-closures and registration to the previous "MLS 1 - TUM City Campus" dataset from 2016.
A more sophisticated fine-registration may be necessary for tasks such as change detection, and the provided translation vectors can be replaced with better results if needed.
If you already have access to the first dataset, you can use the same password and simply replace the "1" in the username with "2".
Dataset details can be found here: [http://s.fhg.de/mls2 (opens in a new tab)].