An object-oriented approach using a top-down and bottom-up process for manipulative action recognition

Li Z, Fritsch J, Wachsmuth S, Sagerer G (2006)
In: Pattern Recognition, Proceedings. Deutsche Arbeitsgemeinschaft für Mustererkennung, Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung (Eds); Lecture Notes in Computer Science, 4174, 4174. Berlin: Springer-Verlag: 212-221.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
herausgebende Körperschaft
Deutsche Arbeitsgemeinschaft für Mustererkennung; Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung
Abstract / Bemerkung
Different from many gesture-based human-robot interaction applications, which focused on the recognition of the interactional or the pointing gestures, this paper proposes a vision-based method for manipulative gesture recognition aiming to achieve natural, proactive, and non-intrusive interaction between humans and robots. The main contributions of the paper are an object-centered scheme for the segmentation and characterization of hand trajectory information, the use of particle filtering methods for an action primitive spotting, and the tight coupling of bottom-up and top-down processing that realizes a task-driven attention filter for low-level recognition steps. In contrast to purely trajectory based techniques, the presented approach is called object-oriented w.r.t. two different aspects: it is object-centered in terms of trajectory features that are defined relative to an object, and it uses object-specific models for action primitives. The system has a two-layer structure recognizing both the HMM-modeled manipulative primitives and the underlying task characterized by the manipulative primitive sequence. The proposed top-down and bottom-up mechanism between the two layers decreases the image processing load and improves the recognition rate.
Erscheinungsjahr
2006
Titel des Konferenzbandes
Pattern Recognition, Proceedings
Serien- oder Zeitschriftentitel
Lecture Notes in Computer Science, 4174
Band
4174
Seite(n)
212-221
ISBN
9783540444121
ISSN
0302-9743
Page URI
https://pub.uni-bielefeld.de/record/1597166

Zitieren

Li Z, Fritsch J, Wachsmuth S, Sagerer G. An object-oriented approach using a top-down and bottom-up process for manipulative action recognition. In: Deutsche Arbeitsgemeinschaft für Mustererkennung, Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung, eds. Pattern Recognition, Proceedings. Lecture Notes in Computer Science, 4174. Vol 4174. Berlin: Springer-Verlag; 2006: 212-221.
Li, Z., Fritsch, J., Wachsmuth, S., & Sagerer, G. (2006). An object-oriented approach using a top-down and bottom-up process for manipulative action recognition. In Deutsche Arbeitsgemeinschaft für Mustererkennung & Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung (Eds.), Lecture Notes in Computer Science, 4174: Vol. 4174. Pattern Recognition, Proceedings (pp. 212-221). Berlin: Springer-Verlag. https://doi.org/10.1007/11861898_22
Li, Zhe, Fritsch, Jannik, Wachsmuth, Sven, and Sagerer, Gerhard. 2006. “An object-oriented approach using a top-down and bottom-up process for manipulative action recognition”. In Pattern Recognition, Proceedings, ed. Deutsche Arbeitsgemeinschaft für Mustererkennung and Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung, 4174:212-221. Lecture Notes in Computer Science, 4174. Berlin: Springer-Verlag.
Li, Z., Fritsch, J., Wachsmuth, S., and Sagerer, G. (2006). “An object-oriented approach using a top-down and bottom-up process for manipulative action recognition” in Pattern Recognition, Proceedings, Deutsche Arbeitsgemeinschaft für Mustererkennung, and Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung eds. Lecture Notes in Computer Science, 4174, vol. 4174, (Berlin: Springer-Verlag), 212-221.
Li, Z., et al., 2006. An object-oriented approach using a top-down and bottom-up process for manipulative action recognition. In Deutsche Arbeitsgemeinschaft für Mustererkennung & Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung, eds. Pattern Recognition, Proceedings. Lecture Notes in Computer Science, 4174. no.4174 Berlin: Springer-Verlag, pp. 212-221.
Z. Li, et al., “An object-oriented approach using a top-down and bottom-up process for manipulative action recognition”, Pattern Recognition, Proceedings, Deutsche Arbeitsgemeinschaft für Mustererkennung and Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung, eds., Lecture Notes in Computer Science, 4174, vol. 4174, Berlin: Springer-Verlag, 2006, pp.212-221.
Li, Z., Fritsch, J., Wachsmuth, S., Sagerer, G.: An object-oriented approach using a top-down and bottom-up process for manipulative action recognition. In: Deutsche Arbeitsgemeinschaft für Mustererkennung and Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung (eds.) Pattern Recognition, Proceedings. Lecture Notes in Computer Science, 4174. 4174, p. 212-221. Springer-Verlag, Berlin (2006).
Li, Zhe, Fritsch, Jannik, Wachsmuth, Sven, and Sagerer, Gerhard. “An object-oriented approach using a top-down and bottom-up process for manipulative action recognition”. Pattern Recognition, Proceedings. Ed. Deutsche Arbeitsgemeinschaft für Mustererkennung and Österreichische Computer Gesellschaft. Arbeitskreis für Mustererkennung. Berlin: Springer-Verlag, 2006.Vol. 4174. Lecture Notes in Computer Science, 4174. 212-221.