TU Darmstadt / ULB / TUbiblio

Visual-Interactive Segmentation of Multivariate Time Series

Bernard, Jürgen and Dobermann, Eduard and Bögl, Markus and Röhlig, Martin and Vögele, Anna and Kohlhammer, Jörn (2016):
Visual-Interactive Segmentation of Multivariate Time Series.
Eurographics Association, Goslar, In: EuroVA 2016, 7th international EuroVis workshop on Visual Analytics, Groningen, The Netherlands, June 6-7, 2016, DOI: 10.2312/eurova.20161121, [Conference or Workshop Item]

Abstract

Choosing appropriate time series segmentation algorithms and relevant parameter values is a challenging problem. In order to choose meaningful candidates it is important that different segmentation results are comparable. We propose a Visual Analytics (VA) approach to address these challenges in the scope of human motion capture data, a special type of multivariate time series data. In our prototype, users can interactively select from a rich set of segmentation algorithm candidates. In an overview visualization, the results of these segmentations can be compared and adjusted with regard to visualizations of raw data. A similarity-preserving colormap further facilitates visual comparison and labeling of segments. We present our prototype and demonstrate how it can ease the choice of winning candidates from a set of results for the segmentation of human motion capture data.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Bernard, Jürgen and Dobermann, Eduard and Bögl, Markus and Röhlig, Martin and Vögele, Anna and Kohlhammer, Jörn
Title: Visual-Interactive Segmentation of Multivariate Time Series
Language: English
Abstract:

Choosing appropriate time series segmentation algorithms and relevant parameter values is a challenging problem. In order to choose meaningful candidates it is important that different segmentation results are comparable. We propose a Visual Analytics (VA) approach to address these challenges in the scope of human motion capture data, a special type of multivariate time series data. In our prototype, users can interactively select from a rich set of segmentation algorithm candidates. In an overview visualization, the results of these segmentations can be compared and adjusted with regard to visualizations of raw data. A similarity-preserving colormap further facilitates visual comparison and labeling of segments. We present our prototype and demonstrate how it can ease the choice of winning candidates from a set of results for the segmentation of human motion capture data.

Publisher: Eurographics Association, Goslar
Uncontrolled Keywords: Guiding Theme: Digitized Work, Guiding Theme: Individual Health, Guiding Theme: Smart City, Research Area: Computer graphics (CG), Research Area: Computer vision (CV), Research Area: Human computer interaction (HCI), Information visualization, Visual analytics, Time series analysis, Data mining, Machine learning, Clustering, Human motion analysis
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: EuroVA 2016, 7th international EuroVis workshop on Visual Analytics
Event Location: Groningen, The Netherlands
Event Dates: June 6-7, 2016
Date Deposited: 08 May 2019 06:40
DOI: 10.2312/eurova.20161121
Export:

Optionen (nur für Redakteure)

View Item View Item