******************************************************************************* Details of the data acquisition, the methods for the detection of moving objects, and original results are published in: Gehrung, J., Hebel, M., Arens, M., Stilla, U., 2017. An approach to extract moving objects from MLS data using a volumetric background representation. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume IV-1/W1, pp. 107-114. DOI: 10.5194/isprs-annals-IV-1-W1-107-2017 The MLS data were supplemented with labels as described in: Zhu, J., Gehrung, J., Huang, R., Borgmann, B., Sun, Z., Hoegner, L., Hebel, M., Xu, Y., Stilla, U., 2020. TUM-MLS-2016: An Annotated Mobile LiDAR Dataset of the TUM City Campus for Semantic Point Cloud Interpretation in Urban Areas. Remote Sens. 2020, 12, 1875. DOI: 10.3390/rs12111875 The dataset you find here is copyrighted by Fraunhofer IOSB and published under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0, https://creativecommons.org/licenses/by-nc-sa/4.0/) When using the data in any publication or for any other purpose, give appropriate credit and cite the above papers. ******************************************************************************* The sensor system comprises two Velodyne HDL-64E. Their measurements have been georeferenced using postprocessed data of an inertial navigation system (Applanix POS LV). Each file in the dataset corresponds to 1/10 sec, which is approximately the time for one rotation of a scanner head. The data can only be downloaded in binary .pcd-format, which is the file format of the Point Cloud Library (PCL, http://pointclouds.org/). In case you want to convert the files to an ASCII format, use the precompiled executable pcl_convert_pcd_ascii_binary[.exe] you can find in a standard installation of the PCL. The available data fields are (1-3): measured 3D-point x/y/z, (4-6): corresponding sensor position x/y/z, (7): reflectance (which is a gray-value) Every .pcd file contains an organized cloud, i.e., the scan pattern of the Velodyne sensors is preserved. The values are NaN in cases where no pulse echo could be received. The test site "TUM City Campus" is located at N 48.149335477777778°, E 11.568528380555556°, 587.1989 m (reference point, WGS84). All point coordinates relate to a local Euclidean coordinate system ENU. The transformation of each 3D-point back to ECEF is given by (as rows of a 4x4 matrix): -0.20053982643488838 -0.72975436304732511 0.653637780140389870 4177139.442822214700 0.979685550579095120 -0.14937937302342402 0.133798448801411370 855052.7445900742900 0.000000000000000000 0.667191406216027790 0.744886318488585660 4728408.463954962800 0.000000000000000000 0.000000000000000000 0.000000000000000000 1.000000000000000000 The infrared image sequence was recorded along with the mobile laser scanning data. The sensor that was used for the data acquisition was a Jenoptik IR-TCM 640 uncooled microbolometer with a field of view of 65.2° x 51.3°. The images of the sequence are provided as 16-bit TIFFs with lossless compression (lzw). An exemplary MATLAB script for tone mapping can be found in the folder ./Examples/ToneMapping_IR The file vehicle-track_ir-frames.txt contains additional meta-information (1): frame number (2-4) position of the sensor carrier x/y/z, (5-7): orientation of the sensor carrier roll/pitch/yaw [°] NB: (2-4) and (5-6) do not represent the sensor pose, but that of the sensor carrier (vehicle). Intrinsic and extrinsic calibration are necessary in order to combine the IR and laser data. [February 2020:] The folder ./IRlaser contains source code that shows how to combine IR and laser data, including estimations of the IR camera's lever arm, boresight angles, and distortion. [January 2020:] The folder ./als2009 contains airborne laser scanning data of the same area which were recorded in 2009. Please see the readme.txt in that folder for details. [February 2021:] The folder ./Labels_Version-2020 contains object class and instance labels as described in https://doi.org/10.3390/rs12111875 Please see that folder for details.