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

TL;DR

This paper introduces a robust method for segmenting repetitive human actions by combining frequency analysis, zero-velocity detection, and adaptive clustering, effective across different motion capture modalities.

Contribution

The paper presents a novel approach that unifies diverse motion data and accurately segments repetitive actions using frequency-based features and adaptive clustering.

Findings

Effective segmentation across different data modalities

Robust to noise and sampling rate variations

Accurate identification of action repetitions

Abstract

In this paper, we propose a method for temporal segmentation of human repetitive actions based on frequency analysis of kinematic parameters, zero-velocity crossing detection, and adaptive k-means clustering. Since the human motion data may be captured with different modalities which have different temporal sampling rate and accuracy (e.g., optical motion capture systems vs. Microsoft Kinect), we first apply a generic full-body kinematic model with an unscented Kalman filter to convert the motion data into a unified representation that is robust to noise. Furthermore, we extract the most representative kinematic parameters via the primary frequency analysis. The sequences are segmented based on zero-velocity crossing of the selected parameters followed by an adaptive k-means clustering to identify the repetition segments. Experimental results demonstrate that for the motion data captured by both the motion capture system and the Microsoft Kinect, our proposed algorithm obtains robust segmentation of repetitive action sequences.