Improving Kinect-Skeleton Estimation

Varování

Publikace nespadá pod Fakultu sportovních studií, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.

Autoři	VALČÍK Jakub SEDMIDUBSKÝ Jan ZEZULA Pavel
Rok publikování	2015
Druh	Článek ve sborníku
Konference	Advanced Concepts for Intelligent Vision Systems (ACIVS 2015), LNCS 9386
Fakulta / Pracoviště MU	Fakulta informatiky
Citace
Doi	http://dx.doi.org/10.1007/978-3-319-25903-1_50
Obor	Informatika
Klíčová slova	Kinect v2; skeleton proportions; bone length estimation; joint accuracy
Popis	Capturing human movement activities through various sensor technologies is becoming more and more important in entertainment, film industry, military, healthcare or sports. The Microsoft Kinect is an example of low-cost capturing technology that enables to digitize human movement into a 3D motion representation. However, the accuracy of this representation is often underestimated which results in decreasing effectiveness of Kinect applications. In this paper, we propose advanced post-processing methods to improve the accuracy of the Kinect skeleton estimation. By evaluating these methods on real-life data we decrease the error in accuracy of measured lengths of bones more than two times.
Související projekty:	Centrum pro multi-modální interpretaci dat velkého rozsahu Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity