TY  - VIDEO
A1  - Meine, Julien
A1  - Voigt, Niklas
A1  - Kremer, Jan-Niklas
A1  - Digakis, Niklas
A1  - Schulte, Max
A1  - Surmann, Hartmut
T1  - 3D point cloud model from the DRZ trainings site
N2  - From the 360° images of the former video (  

 • German rescue robotic center captured...  ) we now generate the 3D point cloud. The UAV needs 3 minutes to capture the outdoor scenario and the hall from inside and outside. The 3D point cloud generation is 5x slower than the video. It uses a VSLAM algorithm to localize the k-frames (green) and with 3 k-frames it use a 360° PatchMatch algorithm implemented at a NVIDIA graphic card (CUDA) to calculated the dense point clouds.The hall ist about 70 x 20 meters.
Y1  - 2023
UR  - https://whge.opus.hbz-nrw.de/frontdoor/index/index/docId/4313
UR  - https://nbn-resolving.org/urn:nbn:de:hbz:1010-opus4-43134
ER  -