Recognition of Gestural Object Reference with Auditory Feedback

Bax I, Bekel H, Heidemann G (2003)
In: Artificial neural networks and neural information processing. Proceedings. Kaynak O (Ed); Lecture notes in computer science, 2712. Berlin: Springer: 425-432.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA
Autor*in
Bax, Ingo; Bekel, Holger; Heidemann, Gunther
Herausgeber*in
Kaynak, Okyay
Abstract / Bemerkung
We present a cognitively motivated vision architecture for the evaluation of pointing gestures. The system views a scene of several structured objects and a pointing human hand. A neural classifier gives an estimation of the pointing direction, then the object correspondence is established using a sub-symbolic representation of both the scene and the pointing direction. The system achieves high robustness because the result (the indicated location) does not primarily depend on the accuracy of the pointing direction classification. Instead, the scene is analysed for low level saliency features to restrict the set of all possible pointing locations to a subset of highly likely locations. This transformation of the "continuous" to a "discrete" pointing problem simultaneously facilitates an auditory feedback whenever the object reference changes, which leads to a significantly improved human-machine interaction.
Erscheinungsjahr
2003
Titel des Konferenzbandes
Artificial neural networks and neural information processing. Proceedings
forms.conference.field.series_title_volume.series_title.label
Lecture notes in computer science
Band
2712
Seite(n)
425-432
Konferenz
Joint International Conference ICANN/ICONIP 2003
Konferenzort
Istanbul, Turkey
Konferenzdatum
2003-06-26 – 2003-06-29
ISBN
3-540-40408-2
Page URI
https://pub.uni-bielefeld.de/record/2714583

Zitieren

Bax I, Bekel H, Heidemann G. Recognition of Gestural Object Reference with Auditory Feedback. In: Kaynak O, ed. Artificial neural networks and neural information processing. Proceedings. Lecture notes in computer science. Vol 2712. Berlin: Springer; 2003: 425-432.
Bax, I., Bekel, H., & Heidemann, G. (2003). Recognition of Gestural Object Reference with Auditory Feedback. In O. Kaynak (Ed.), Lecture notes in computer science: Vol. 2712. Artificial neural networks and neural information processing. Proceedings (pp. 425-432). Berlin: Springer.
Bax, I., Bekel, H., and Heidemann, G. (2003). “Recognition of Gestural Object Reference with Auditory Feedback” in Artificial neural networks and neural information processing. Proceedings, Kaynak, O. ed. Lecture notes in computer science, vol. 2712, (Berlin: Springer), 425-432.
Bax, I., Bekel, H., & Heidemann, G., 2003. Recognition of Gestural Object Reference with Auditory Feedback. In O. Kaynak, ed. Artificial neural networks and neural information processing. Proceedings. Lecture notes in computer science. no.2712 Berlin: Springer, pp. 425-432.
I. Bax, H. Bekel, and G. Heidemann, “Recognition of Gestural Object Reference with Auditory Feedback”, Artificial neural networks and neural information processing. Proceedings, O. Kaynak, ed., Lecture notes in computer science, vol. 2712, Berlin: Springer, 2003, pp.425-432.
Bax, I., Bekel, H., Heidemann, G.: Recognition of Gestural Object Reference with Auditory Feedback. In: Kaynak, O. (ed.) Artificial neural networks and neural information processing. Proceedings. Lecture notes in computer science. 2712, p. 425-432. Springer, Berlin (2003).
Bax, Ingo, Bekel, Holger, and Heidemann, Gunther. “Recognition of Gestural Object Reference with Auditory Feedback”. Artificial neural networks and neural information processing. Proceedings. Ed. Okyay Kaynak. Berlin: Springer, 2003.Vol. 2712. Lecture notes in computer science. 425-432.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:29Z
MD5 Prüfsumme
2fa823ddb8828b907224fd290f5ce457

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Suchen in

Google Scholar
ISBN Suche