Persistent homology of attractors for action recognition

Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Scopus citations

Abstract

In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis. We model human actions using the topological features of the attractor of the dynamical system. We reconstruct the phase-space of time series corresponding to actions using time-delay embedding, and compute the persistent homology of the phase-space reconstruction. In order to better represent the topological properties of the phase-space, we incorporate the temporal adjacency information when computing the homology groups. The persistence of these homology groups encoded using persistence diagrams are used as features for the actions. Our experiments with action recognition using these features demonstrate that the proposed approach outperforms other baseline methods.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages4150-4154
Number of pages5
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2016-August
ISSN (Print)1522-4880

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
Country/TerritoryUnited States
CityPhoenix
Period9/25/169/28/16

Keywords

  • Persistence diagram
  • Persistent homology
  • Phase-space reconstruction

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Persistent homology of attractors for action recognition'. Together they form a unique fingerprint.

Cite this