English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a method for temporal segmentation of humanrepetitive actions based on frequency analysis of kinematic parameters,zero-velocity crossing detection, and adaptive k-means clustering. Since thehuman motion data may be captured with different modalities which havedifferent temporal sampling rate and accuracy (e.g., optical motion capturesystems vs. Microsoft Kinect), we first apply a generic full-body kinematicmodel with an unscented Kalman filter to convert the motion data into a unifiedrepresentation that is robust to noise. Furthermore, we extract the mostrepresentative kinematic parameters via the primary frequency analysis. Thesequences are segmented based on zero-velocity crossing of the selectedparameters followed by an adaptive k-means clustering to identify therepetition segments. Experimental results demonstrate that for the motion datacaptured by both the motion capture system and the Microsoft Kinect, ourproposed algorithm obtains robust segmentation of repetitive action sequences.

Unsupervised Temporal Segmentation of Repetitive Human Actions Based on Kinematic Modeling and Frequency Analysis