Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Visual-interactive semi-supervised labeling of human motion capture data

: Bernard, Jürgen; Dobermann, Eduard; Vögele, Anna; Krüger, Björn; Kohlhammer, Jörn; Fellner, Dieter W.


Wischgoll, Thomas (Ed.) ; Society for Imaging Science and Technology -IS&T-:
IS&T International Symposium on Electronic Imaging. Visualization and Data Analysis 2017. Online resource : Jan 29 - Feb 2, 2017, Burlingame, California
Springfield/Va.: IS&T, 2017
International Symposium on Electronic Imaging (EI) <2017, Burlingame/Calif.>
Fraunhofer IGD ()
visual analytic; information visualization; motion capturing; motion segmentation; human motion analysis; segmentation; Interactive Segmentation; Labeling; machine learning; visual data mining; data mining; Guiding Theme: Digitized Work; Guiding Theme: Individual Health; Research Area: Human computer interaction (HCI)

The characterization and abstraction of large multivariate time series data often poses challenges with respect to effectiveness or efficiency. Using the example of human motion capture data challenges exist in creating compact solutions that still reflect semantics and kinematics in a meaningful way. We present a visual-interactive approach for the semi-supervised labeling of human motion capture data. Users are enabled to assign labels to the data which can subsequently be used to represent the multivariate time series as sequences of motion classes. The approach combines multiple views supporting the user in the visual-interactive labeling process. Visual guidance concepts further ease the labeling process by propagating the results of supportive algorithmic models. The abstraction of motion capture data to sequences of event intervals allows overview and detail-on-demand visualizations even for large and heterogeneous data collections. The guided selection of candidate data for the extension and improvement of the labeling closes the feedback loop of the semi-supervised workflow. We demonstrate the effectiveness and the efficiency of the approach in two usage scenarios, taking visual-interactive learning and human motion synthesis as examples.