View-adaptive Manipulative Action Recognition for Robot Companions

Li Z, Wachsmuth S, Fritsch J, Sagerer G (2007)
In: Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Restricted iros07_final_535.pdf
Abstract / Bemerkung
This paper puts forward an approach for a mobile robot to recognize the human’s manipulative actions from different single camera views. While most of the related work in action recognition assume a fixed static camera view that is the same for training and testing, such kind of constraints do not apply for mobile robot companions. We propose a recognition scheme that is able to generalize an action model, that has been learned from a very few data items observed from a single camera view, to variant view points and different settings. We tackle the problem of compensating the view dependence of 2D motion models on three different levels. Firstly, we pre-segment the trajectories based on an object vicinity that depends on the camera tilt and object detections. Secondly, an interactive feature vector is designed that represents the relative movements between the human hand and the objects. Thirdly, we propose an adaptive HMM-based matching process that is based on a particle filter and includes a dynamically adjusted scaling parameter that models the systematic error of the view dependency. Finally, we use a two-layered approach for task recognition which decouples the task knowledge from the view dependent primitive recognition. The results of experiments in an office environment show the applicability of this approach.
Stichworte
hidden Markov model; view-adaptive; action recognition; variant viewangles; manipulative gesture; particle filter
Erscheinungsjahr
2007
Titel des Konferenzbandes
Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Konferenz
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Konferenzort
San Diego, CA, USA
Page URI
https://pub.uni-bielefeld.de/record/1991931

Zitieren

Li Z, Wachsmuth S, Fritsch J, Sagerer G. View-adaptive Manipulative Action Recognition for Robot Companions. In: Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE; 2007.
Li, Z., Wachsmuth, S., Fritsch, J., & Sagerer, G. (2007). View-adaptive Manipulative Action Recognition for Robot Companions. Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) IEEE.
Li, Z., Wachsmuth, S., Fritsch, J., and Sagerer, G. (2007). “View-adaptive Manipulative Action Recognition for Robot Companions” in Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE).
Li, Z., et al., 2007. View-adaptive Manipulative Action Recognition for Robot Companions. In Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE.
Z. Li, et al., “View-adaptive Manipulative Action Recognition for Robot Companions”, Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2007.
Li, Z., Wachsmuth, S., Fritsch, J., Sagerer, G.: View-adaptive Manipulative Action Recognition for Robot Companions. Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2007).
Li, Zhe, Wachsmuth, Sven, Fritsch, Jannik, and Sagerer, Gerhard. “View-adaptive Manipulative Action Recognition for Robot Companions”. Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2007.
Volltext(e)
Name
iros07_final_535.pdf
Access Level
Restricted Closed Access
Zuletzt Hochgeladen
2019-09-06T08:57:15Z
MD5 Prüfsumme
2be101e0517f0ac670688d6b63a33dd4

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar