Refine
Year of publication
Institute
- Fachbereich Maschinenbau und Mechatronik (868) (remove)
Document Type
- Article (484)
- Conference Proceeding (207)
- Book (99)
- Part of a Book (32)
- Lecture (21)
- Report (8)
- Bachelor Thesis (5)
- Contribution to a Periodical (3)
- Doctoral Thesis (2)
- Master's Thesis (2)
Keywords
- Rapid Prototyping (8)
- Rapid prototyping (6)
- Übungsklausur (5)
- Additive manufacturing (4)
- Gamification (4)
- Fertigungsverfahren (3)
- Mikrosystemtechnik (3)
- Regelungstechnik (3)
- SLM (3)
- additive manufacturing (3)
Eine SPS im Kraftfahrzeug? Das geht ja gar nicht – da gibt es doch all die Hersteller für Kfz-Steuergeräte, die konfigurierbare Hardware anbieten. Im Prinzip ja, aber leider sind gerade die Sensoren oder Aktoren nicht ansteuerbar, die der Entwickler genau für sein aktuelles Projekt benötigt. Dieser Beitrag gibt einen kleinen Einblick in neue Möglichkeiten des Rapid Prototyping für mechatronische Systeme auf der Basis von Speicherprogrammierbaren Steuerungen (SPS).
We present an automated pipeline for the generation of synthetic datasets for six-dimension (6D) object pose estimation. Therefore, a completely automated generation process based on predefined settings is developed, which enables the user to create large datasets with a minimum of interaction and which is feasible for applications with a high object variance. The pipeline is based on the Unreal 4 (UE4) game engine and provides a high variation for domain randomization, such as object appearance, ambient lighting, camera-object transformation and distractor density. In addition to the object pose and bounding box, the metadata includes all randomization parameters, which enables further studies on randomization parameter tuning. The developed workflow is adaptable to other 3D objects and UE4 environments. An exemplary dataset is provided including five objects of the Yale-CMU-Berkeley (YCB) object set. The datasets consist of 6 million subsegments using 97 rendering locations in 12 different UE4 environments. Each dataset subsegment includes one RGB image, one depth image and one class segmentation image at pixel-level.