Full metadata record
DC FieldValueLanguage
dc.contributor.authorZiegler, Matthias-
dc.date.accessioned2022-07-06T08:29:29Z-
dc.date.available2022-07-06T08:29:29Z-
dc.date.issued2022-06-03-
dc.identifier.urihttps://fordatis.fraunhofer.de/handle/fordatis/273-
dc.identifier.urihttp://dx.doi.org/10.24406/fordatis/202-
dc.descriptionThis dataset is composed from three different scenes with a varying number of takes per scene. The images have been generated using CARLA, a framework for autonomeous driving. In the dataset, an autonomeous car is exploring an urban area under different lighting and weather conditions. In each take, the car is equipped with three front-facing cameras capturing the scenery. Besides pure RGB image data, the dataset features ground-truth depth information encoded as described here: https://carla.readthedocs.io/en/latest/ref_sensors/#depth-camera The camera parameters and capture setup is as follows: Field of view: 110° Resolution: 1920 x 1080 Number of takes: Scene 1: 41 Scene 2: 23 Scene 3: 20 Camera baseline Scene 1: 0.280833m (2.17m/12) Scene 2 and 3: 0.1m-
dc.description.abstractThis dataset is composed from three different scenes with a varying number of takes per scene. The images have been generated using CARLA, a framework for autonomeous driving. In the dataset, an autonomeous car is exploring an urban area under different lighting and weather conditions. In each take, the car is equipped with three front-facing cameras capturing the scenery. Besides pure RGB image data, the dataset features ground-truth depth information encoded as described here: https://carla.readthedocs.io/en/latest/ref_sensors/#depth-camera The camera parameters and capture setup is as follows: Field of view: 110° Resolution: 1920 x 1080 Number of takes: Scene 1: 41 Scene 2: 23 Scene 3: 20 Camera baseline Scene 1: 0.280833m (2.17m/12) Scene 2 and 3: 0.1men
dc.language.isoenen
dc.publisherCoffee Bean State University-
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectmulti-cameraen
dc.subjectdeep-learningen
dc.subjectdepth-reconstructionen
dc.subject.ddcDDC::000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::004 Datenverarbeitung; Informatiken
dc.subject.ddcDDC::600 Technik, Medizin, angewandte Wissenschaften::600 Technik::600 Technik, Technologieen
dc.titleDataset for multi-camera depth reconstructionen
dc.typeImageen
dc.contributor.funderBundesministerium für Bildung und Forschung BMBF (Deutschland)en
fordatis.groupIUK-Technologieen
fordatis.instituteIIS Fraunhofer-Institut für Integrierte Schaltungenen
fordatis.rawdatafalseen
fordatis.sponsorship.projectid01IS1907Aen
fordatis.sponsorship.projectnameKI-Labor Systemdesign für Maschinelles Lernen in Anwendungen der Signalverarbeitungen
fordatis.sponsorship.projectacronymKISSen
dc.date.updated2022-06-03T08:20:19Z-
fordatis.date.start2020-11-01-
fordatis.date.end2020-11-30-
Appears in Collections:Fraunhofer-Institut für Integrierte Schaltungen IIS

Files in This Item:
File Description SizeFormat 
Scene_1.tar177,79 GBTARDownload/Open
Scene_2.tar203,65 GBTARDownload/Open
Scene_3.tar172,87 GBTARDownload/Open
Scene_3.tar172,87 GBTARDownload/Open


This item is licensed under a Creative Commons License Creative Commons