Real-Time Hierarchical Scene Segmentation and Classification

Ückermann A, Elbrechter C, Haschke R, Ritter H (2014)
In: 2014 IEEE-RAS International Conference on Humanoid Robots. Piscataway, NJ: IEEE: 225-231.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Campus/VPN paper.pdf 5.09 MB
Abstract / Bemerkung
We present an extension to our previously reported real-time scene segmentation approach which generates a complete hierarchy of segmentation hypotheses. An object classifier traverses the hypotheses tree in a top-down manner, returning good object hypotheses and thus helping to select the correct level of abstraction for segmentation and avoiding over- and under-segmentation. Combining model-free, bottom-up segmentation results with trained, top-down classification results, our approach improves both classification and segmentation results. It allows for identification of object parts and complete objects (e.g. a mug composed from the handle and its inner and outer surfaces) in a uniform and scalable framework. We discuss its advantages compared to existing approaches and present qualitative results. Finally, the approach is applied in an interactive robotics scenario to help the robot grasp objects in response to verbal commands.
Stichworte
3D; Segmentation; Computer Vision
Erscheinungsjahr
2014
Titel des Konferenzbandes
2014 IEEE-RAS International Conference on Humanoid Robots
Seite(n)
225-231
Konferenz
IEEE-RAS International Conference on Humanoid Robots (Humanoids 2014)
Konferenzort
Madrid, Spain
Konferenzdatum
2014-11-18 – 2014-11-20
ISBN
978-1-4799-7174-9
Page URI
https://pub.uni-bielefeld.de/record/2737409

Zitieren

Ückermann A, Elbrechter C, Haschke R, Ritter H. Real-Time Hierarchical Scene Segmentation and Classification. In: 2014 IEEE-RAS International Conference on Humanoid Robots. Piscataway, NJ: IEEE; 2014: 225-231.
Ückermann, A., Elbrechter, C., Haschke, R., & Ritter, H. (2014). Real-Time Hierarchical Scene Segmentation and Classification. 2014 IEEE-RAS International Conference on Humanoid Robots, 225-231. Piscataway, NJ: IEEE. https://doi.org/10.1109/HUMANOIDS.2014.7041364
Ückermann, A., Elbrechter, C., Haschke, R., and Ritter, H. (2014). “Real-Time Hierarchical Scene Segmentation and Classification” in 2014 IEEE-RAS International Conference on Humanoid Robots (Piscataway, NJ: IEEE), 225-231.
Ückermann, A., et al., 2014. Real-Time Hierarchical Scene Segmentation and Classification. In 2014 IEEE-RAS International Conference on Humanoid Robots. Piscataway, NJ: IEEE, pp. 225-231.
A. Ückermann, et al., “Real-Time Hierarchical Scene Segmentation and Classification”, 2014 IEEE-RAS International Conference on Humanoid Robots, Piscataway, NJ: IEEE, 2014, pp.225-231.
Ückermann, A., Elbrechter, C., Haschke, R., Ritter, H.: Real-Time Hierarchical Scene Segmentation and Classification. 2014 IEEE-RAS International Conference on Humanoid Robots. p. 225-231. IEEE, Piscataway, NJ (2014).
Ückermann, André, Elbrechter, Christof, Haschke, Robert, and Ritter, Helge. “Real-Time Hierarchical Scene Segmentation and Classification”. 2014 IEEE-RAS International Conference on Humanoid Robots. Piscataway, NJ: IEEE, 2014. 225-231.
Volltext(e)
Name
paper.pdf 5.09 MB
Access Level
Campus/VPN UniBi Only
Zuletzt Hochgeladen
2021-04-07T19:03:55Z
MD5 Prüfsumme
d875562a2fa004b5faa438b70bfdae81

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche