Main content

Home

Menu

Loading wiki pages...

View
Wiki Version:
# Salzburg Bicycle LiDAR Data Set (SBLD) ## Introduction ![enter image description here][1] Source Left Image: [[1]] The Salzburg Bicycle LiDAR Data Set (SBLD) was recorded with five LIVOX HORIZON LiDARs on a smart bycicle. Their field of view are aligned by hand using the point cloud library and ROS2. Please refer to the thesis attached to the project files for more information about the label distribution in the data set and a more fine-grained description of the data set including images. This data set was created as part of my master's thesis and please refer to the SBLD part of my master's thesis [here][2], where you can find more information about the data set and also some images. ## Files The data set is currently split into ``labeled`` and ``unlabeled``. Each folder has a ``sequences`` folder inside. Please extract the archives and copy the content of each ``sequences`` into ``labeled/sequences`` and ``unlabeled/sequences`` respectively. In each sequence, there is also an image from Google Maps, showing the sequence from a bird's eye view [[1]]. ## Folder structure and format The SBLD follows the structure of the semantic KITTI data set, as described [here][3]. ## Data Conversion and Labeling LiVOX HORIZON LiDARs use a ROS2 node to send point clouds via ROS2 topics. Those five topics were read, the respective point clouds transformed and merged into one. The intermediate format are .pcd files which are then converted with tools such as [pcd2bin][4] into the Semantic KITTI binary format. Each sequence holds a ``poses.txt`` file which holds the relative positions of each point cloud to view them as a whole, properly aligned sequence inside Point Labeler. The ``poses.txt`` was generated by using [KISS ICP][5], which is a SLAM approach. Labeling of the data set was conducted with [Point Labeler][6], which can read .bin point cloud files and interpret an existing ``poses.txt`` file. ## Current Sequences as of 27.02.23 |# |location|point clouds|date|labeled| |-----------------------------------------------------------------|---|---|---|---| |01|Gabelsbergerstrasse <-> Kiesel|500|22.07.2022|no| |02| Jakob-Haringer-Strasse|300|05.09.2022|yes| |03| Ischlerbahn - Kreuzung Söllheimerstrasse |35| 05.09.2022| yes| |04| Ischlerbahn - Gnigl - Kurzes Stück| 30 |05.09.2022| yes| |05| Alterbach -> Itzlinger Hauptstrasse |1020| 05.09.2022 |yes| |06| Itzlinger Hauptstrasse -> Salzach| 373|05.09.2022| yes| |07 |Salzachbrücke -> Kraftwerk Lehen| 688|05.09.2022| yes| |08 |Kraftwerk Lehen -> Franz-Ofner-Strasse| 400 |05.09.2022| no| |09| Bahnhof Bergheim -> Muntigl| 909 |05.09.2022 |yes| |10 |Kraftwerk Lehen -> Glanspitz Park Süd| 700| 05.09.2022 |yes| |11 |Uni Nonntal -> Hellbrunner Allee |909 |05.09.2022| yes| |12| Kraftwerk Lehen -> Lehener Park |501| 05.09.2022 |no| |13| Muntigl -> Bahnhof Bergheim| 660|05.09.2022 |no| |14| Hellbrunner Allee mit Feldweg |550| 05.09.2022 |yes| |15| Lehener Park| 787| 05.09.2022| no| |16| Ischlerbahn - Kurzes Waldstück |23 |06.09.2022 |yes| |17| Lehener Park -> Eisenbahnbrücke Mülln |520| 05.09.2022| no| |18 |Ischlerbahn - Waldstück Hallwang| 393| 06.09.2022| yes| |19| Mülln -> Rot-Kreuz-Parkplatz|622 |05.09.2022|no| |20|Mozartsteg -> Karolinenbrücke| 866| 05.09.2022| no| |21| Mozartsteg -> Feingold Steg |657| 05.09.2022| no| |22| Müllnersteg -> Pioniersteg |601| 05.09.2022|no| |23| Salzachbrücke -> Bahnhof Bergheim |930| 05.09.2022 |yes| |24| Salzachbrücke |20| 06.09.2022| yes| |25| Ischlerbahn - Möslkapelle -> Geisbichlweg| 753| 06.09.2022 |yes| |26| Glanspitz Park - Nord|405| 06.09.2022| no| |27| Ischlerbahn - Wiese Hallwang| 975 |06.09.2022| yes| |28| Ischlerbahn - Gnigl |881 |06.09.2022 |yes| |||||| ||labeled|9486||| ||unlabeled|6522||| ||total|16008||| [1]: https://mfr.osf.io/export?url=https://osf.io/download/qb279/?direct=&mode=render&format=2400x2400.jpeg [2]: https://osf.io/dxuze [3]: http://www.semantic-kitti.org/dataset.html [4]: https://github.com/leofansq/Tools_RosBag2KITTI/blob/master/pcd2bin/pcd2bin.cpp [5]: https://github.com/PRBonn/kiss-icp [6]: https://github.com/jbehley/point_labeler [[1]] Google. Google Maps. https://www.google.com/maps/, Sidst set 19/10-2022, 2022.
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
Accept
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.
Accept
×

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.