Efficient Unsupervised Temporal Segmentation of Motion Data

TL;DR

This paper presents an unsupervised method for segmenting and clustering human motion data into meaningful actions using neighborhood graphs, feature bundling, and motion symmetry, applicable across various sensor modalities.

Contribution

The authors introduce a novel unsupervised approach that combines neighborhood graphs, feature bundling, and symmetry analysis for robust motion segmentation and primitive clustering without user input.

Findings

Effective segmentation across multiple sensor types

Robustness to noise through feature bundling

Unsupervised detection of semantic motion primitives

Abstract

We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence. We use neighbourhood graphs for the partitioning and the similarity information in the graph is further exploited to cluster the motion primitives into larger entities of semantic significance. The method requires no assumptions about the motion sequences at hand and no user interaction is required for the segmentation or clustering. In addition, we introduce a feature bundling preprocessing technique to make the segmentation more robust to noise, as well as a notion of motion symmetry for more refined primitive detection. We test our method on several sensor modalities, including markered and markerless motion capture as well as on electromyograph and accelerometer recordings. The results highlight our system's capabilities for both segmentation and for analysis of the finer structures of motion data, all in a completely unsupervised manner.