On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition

Anuj Srivastava, Pavan Turaga, Sebastian Kurtek

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

In this paper we summarize recent advances in shape analysis and shape-based activity recognition problems with a focus on techniques that use tools from differential geometry and statistics. We start with general goals and challenges faced in shape analysis, followed by a summary of the basic ideas, strengths and limitations, and applications of different mathematical representations used in shape analyses of 2D and 3D objects. These representations include point sets, curves, surfaces, level sets, deformable templates, medial representations, and other feature-based methods. We discuss some common choices of Riemannian metrics and computational tools used for evaluating geodesic paths and geodesic distances for several of these shape representations. Then, we study the use of Riemannian frameworks in statistical modeling of variability within shape classes. Next, we turn to models and algorithms for activity analysis from various perspectives. We discuss how mathematical representations for human shape and its temporal evolutions in videos lead to analyses over certain special manifolds. We discuss the various choices of shape features, and parametric and non-parametric models for shape evolution, and how these choices lead to appropriate manifold-valued constraints. We discuss applications of these methods in gait-based biometrics, action recognition, and video summarization and indexing. For reader convenience, we also provide a short overview of the relevant tools from geometry and statistics on manifolds in the Appendix.

Original languageEnglish (US)
Pages (from-to)398-416
Number of pages19
JournalImage and Vision Computing
Volume30
Issue number6-7
DOIs
StatePublished - Jun 2012

Fingerprint

Statistics
Geometry
Biometrics

Keywords

  • Activity recognition
  • Analytic manifolds
  • Elastic shape analysis
  • Riemannian shape metrics
  • Static and video image data
  • Video analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition. / Srivastava, Anuj; Turaga, Pavan; Kurtek, Sebastian.

In: Image and Vision Computing, Vol. 30, No. 6-7, 06.2012, p. 398-416.

Research output: Contribution to journalArticle

@article{dcc4ced822ab4cf1b5e6dd7f65e8661d,
title = "On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition",
abstract = "In this paper we summarize recent advances in shape analysis and shape-based activity recognition problems with a focus on techniques that use tools from differential geometry and statistics. We start with general goals and challenges faced in shape analysis, followed by a summary of the basic ideas, strengths and limitations, and applications of different mathematical representations used in shape analyses of 2D and 3D objects. These representations include point sets, curves, surfaces, level sets, deformable templates, medial representations, and other feature-based methods. We discuss some common choices of Riemannian metrics and computational tools used for evaluating geodesic paths and geodesic distances for several of these shape representations. Then, we study the use of Riemannian frameworks in statistical modeling of variability within shape classes. Next, we turn to models and algorithms for activity analysis from various perspectives. We discuss how mathematical representations for human shape and its temporal evolutions in videos lead to analyses over certain special manifolds. We discuss the various choices of shape features, and parametric and non-parametric models for shape evolution, and how these choices lead to appropriate manifold-valued constraints. We discuss applications of these methods in gait-based biometrics, action recognition, and video summarization and indexing. For reader convenience, we also provide a short overview of the relevant tools from geometry and statistics on manifolds in the Appendix.",
keywords = "Activity recognition, Analytic manifolds, Elastic shape analysis, Riemannian shape metrics, Static and video image data, Video analysis",
author = "Anuj Srivastava and Pavan Turaga and Sebastian Kurtek",
year = "2012",
month = "6",
doi = "10.1016/j.imavis.2012.03.006",
language = "English (US)",
volume = "30",
pages = "398--416",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",
number = "6-7",

}

TY - JOUR

T1 - On advances in differential-geometric approaches for 2D and 3D shape analyses and activity recognition

AU - Srivastava, Anuj

AU - Turaga, Pavan

AU - Kurtek, Sebastian

PY - 2012/6

Y1 - 2012/6

N2 - In this paper we summarize recent advances in shape analysis and shape-based activity recognition problems with a focus on techniques that use tools from differential geometry and statistics. We start with general goals and challenges faced in shape analysis, followed by a summary of the basic ideas, strengths and limitations, and applications of different mathematical representations used in shape analyses of 2D and 3D objects. These representations include point sets, curves, surfaces, level sets, deformable templates, medial representations, and other feature-based methods. We discuss some common choices of Riemannian metrics and computational tools used for evaluating geodesic paths and geodesic distances for several of these shape representations. Then, we study the use of Riemannian frameworks in statistical modeling of variability within shape classes. Next, we turn to models and algorithms for activity analysis from various perspectives. We discuss how mathematical representations for human shape and its temporal evolutions in videos lead to analyses over certain special manifolds. We discuss the various choices of shape features, and parametric and non-parametric models for shape evolution, and how these choices lead to appropriate manifold-valued constraints. We discuss applications of these methods in gait-based biometrics, action recognition, and video summarization and indexing. For reader convenience, we also provide a short overview of the relevant tools from geometry and statistics on manifolds in the Appendix.

AB - In this paper we summarize recent advances in shape analysis and shape-based activity recognition problems with a focus on techniques that use tools from differential geometry and statistics. We start with general goals and challenges faced in shape analysis, followed by a summary of the basic ideas, strengths and limitations, and applications of different mathematical representations used in shape analyses of 2D and 3D objects. These representations include point sets, curves, surfaces, level sets, deformable templates, medial representations, and other feature-based methods. We discuss some common choices of Riemannian metrics and computational tools used for evaluating geodesic paths and geodesic distances for several of these shape representations. Then, we study the use of Riemannian frameworks in statistical modeling of variability within shape classes. Next, we turn to models and algorithms for activity analysis from various perspectives. We discuss how mathematical representations for human shape and its temporal evolutions in videos lead to analyses over certain special manifolds. We discuss the various choices of shape features, and parametric and non-parametric models for shape evolution, and how these choices lead to appropriate manifold-valued constraints. We discuss applications of these methods in gait-based biometrics, action recognition, and video summarization and indexing. For reader convenience, we also provide a short overview of the relevant tools from geometry and statistics on manifolds in the Appendix.

KW - Activity recognition

KW - Analytic manifolds

KW - Elastic shape analysis

KW - Riemannian shape metrics

KW - Static and video image data

KW - Video analysis

UR - http://www.scopus.com/inward/record.url?scp=84862570464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862570464&partnerID=8YFLogxK

U2 - 10.1016/j.imavis.2012.03.006

DO - 10.1016/j.imavis.2012.03.006

M3 - Article

AN - SCOPUS:84862570464

VL - 30

SP - 398

EP - 416

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 6-7

ER -