Invariant representation for user independent motion recognition

Matteo Saveriano, Dongheui Lee

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

11 Zitate (Scopus)

Abstract

Human gesture recognition is of importance for smooth and efficient human robot interaction. One of difficulties in gesture recognition is that different actors have different styles in performing even same gestures. In order to move towards more realistic scenarios, a robot is required to handle not only different users, but also different view points and noisy incomplete data from onboard sensors on the robot. Facing these challenges, we propose a new invariant representation of rigid body motions, which is invariant to translation, rotation and scaling factors. For classification, Hidden Markov Models based approach and Dynamic Time Warping based approach are modified by weighting the importances of body parts. The proposed method is tested with two Kinect datasets and it is compared with another invariant representation and a typical non-invariant representation. The experimental results show good recognition performance of our proposed approach.

OriginalspracheEnglisch
Titel22nd IEEE International Symposium on Robot and Human Interactive Communication
Untertitel"Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013
Seiten650-655
Seitenumfang6
DOIs
PublikationsstatusVeröffentlicht - 2013
Extern publiziertJa
Veranstaltung22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013 - Gyeongju, Südkorea
Dauer: 26 Aug. 201329 Aug. 2013

Publikationsreihe

NameProceedings - IEEE International Workshop on Robot and Human Interactive Communication

Konferenz

Konferenz22nd IEEE International Symposium on Robot and Human Interactive Communication: "Living Together, Enjoying Together, and Working Together with Robots!", IEEE RO-MAN 2013
Land/GebietSüdkorea
OrtGyeongju
Zeitraum26/08/1329/08/13

Fingerprint

Untersuchen Sie die Forschungsthemen von „Invariant representation for user independent motion recognition“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren