Persistent homology of attractors for action recognition

Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga

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

5 Citations (Scopus)

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
Volume2016-August
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

Other

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

Fingerprint

Time series
Data acquisition
Time delay
Dynamical systems
Experiments

Keywords

  • Persistence diagram
  • Persistent homology
  • Phase-space reconstruction

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Venkataraman, V., Ramamurthy, K. N., & Turaga, P. (2016). Persistent homology of attractors for action recognition. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 4150-4154). [7533141] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7533141

Persistent homology of attractors for action recognition. / Venkataraman, Vinay; Ramamurthy, Karthikeyan Natesan; Turaga, Pavan.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 4150-4154 7533141.

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

Venkataraman, V, Ramamurthy, KN & Turaga, P 2016, Persistent homology of attractors for action recognition. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7533141, IEEE Computer Society, pp. 4150-4154, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7533141
Venkataraman V, Ramamurthy KN, Turaga P. Persistent homology of attractors for action recognition. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 4150-4154. 7533141 https://doi.org/10.1109/ICIP.2016.7533141
Venkataraman, Vinay ; Ramamurthy, Karthikeyan Natesan ; Turaga, Pavan. / Persistent homology of attractors for action recognition. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 4150-4154
@inproceedings{1c368e17ca374bcfbe3d288802c0446e,
title = "Persistent homology of attractors for action recognition",
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.",
keywords = "Persistence diagram, Persistent homology, Phase-space reconstruction",
author = "Vinay Venkataraman and Ramamurthy, {Karthikeyan Natesan} and Pavan Turaga",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7533141",
language = "English (US)",
volume = "2016-August",
pages = "4150--4154",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Persistent homology of attractors for action recognition

AU - Venkataraman, Vinay

AU - Ramamurthy, Karthikeyan Natesan

AU - Turaga, Pavan

PY - 2016/8/3

Y1 - 2016/8/3

N2 - 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.

AB - 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.

KW - Persistence diagram

KW - Persistent homology

KW - Phase-space reconstruction

UR - http://www.scopus.com/inward/record.url?scp=85006721604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006721604&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7533141

DO - 10.1109/ICIP.2016.7533141

M3 - Conference contribution

VL - 2016-August

SP - 4150

EP - 4154

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -