Year: 2013
Type: article
Abstract: Human gesture recognition is of importance for smooth and efficient human robot interaction.If the robot understands what the human is doing, then it can select and adapt its behaviours coherently with human's needs, guaranteeing a safe and useful cooperation.We aim at making the robot capable of recognizing actions performed by different people in slightly different manners and from different view points, as shown in Fig. 1.To this end, we propose a new compact representation of a 3D motion, which is invariant to rotations, translations and linear scaling factors.This representation consists of two scalar quantities for each rigid body:
Authors: Matteo Saveriano, Dongheui Lee
Institution: Technical University of Munich
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G3026858508
OpenAlex ID: W2751417692
