View-invariant human activity recognition based on shape and motion features

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous approaches on activity recognition focus on recognition from a single view and ignore the issue of view invariance, and they deal with recognizing a single activity. There are only few published algorithms for segmenting and recognizing complex activities that are composed of more than one activity. In this paper, we present a view invariant human activity recognition approach that uses both motion and shape information. An augmented vector of both optical flow features as well as eigen shape features is used to represent motion and shape of the body in the region of interest in each frame of the sequence. Each activity is represented by a set of hidden Markov models, where each model represents the activity from a different viewing direction, to realize the view invariance. Also, we present a voting-based approach to automatically and effectively segment and recognize complex activities. Experiments on two sets of video clips of different activities show that our method is effective.

Original languageEnglish
Pages (from-to)235-243
Number of pages9
JournalInternational Journal of Robotics and Automation
Volume22
Issue number3
StatePublished - Oct 29 2007

Fingerprint

Activity Recognition
Invariance
Invariant
Motion
Optical flows
Hidden Markov models
Computer vision
Experiments
Shape Feature
Human
Optical Flow
Region of Interest
Image Sequence
Voting
Computer Vision
Markov Model

Keywords

  • Background subtraction
  • Eigen shape
  • Fusion
  • Hidden Markov model
  • Human activity recognition
  • View invariance

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

View-invariant human activity recognition based on shape and motion features. / Niu, F.; Abdel-Mottaleb, Mohamed.

In: International Journal of Robotics and Automation, Vol. 22, No. 3, 29.10.2007, p. 235-243.

Research output: Contribution to journalArticle

@article{ef5c3a580e934d9e895b3180e0013e08,
title = "View-invariant human activity recognition based on shape and motion features",
abstract = "Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous approaches on activity recognition focus on recognition from a single view and ignore the issue of view invariance, and they deal with recognizing a single activity. There are only few published algorithms for segmenting and recognizing complex activities that are composed of more than one activity. In this paper, we present a view invariant human activity recognition approach that uses both motion and shape information. An augmented vector of both optical flow features as well as eigen shape features is used to represent motion and shape of the body in the region of interest in each frame of the sequence. Each activity is represented by a set of hidden Markov models, where each model represents the activity from a different viewing direction, to realize the view invariance. Also, we present a voting-based approach to automatically and effectively segment and recognize complex activities. Experiments on two sets of video clips of different activities show that our method is effective.",
keywords = "Background subtraction, Eigen shape, Fusion, Hidden Markov model, Human activity recognition, View invariance",
author = "F. Niu and Mohamed Abdel-Mottaleb",
year = "2007",
month = "10",
day = "29",
language = "English",
volume = "22",
pages = "235--243",
journal = "International Journal of Robotics and Automation",
issn = "0826-8185",
publisher = "ACTA Press",
number = "3",

}

TY - JOUR

T1 - View-invariant human activity recognition based on shape and motion features

AU - Niu, F.

AU - Abdel-Mottaleb, Mohamed

PY - 2007/10/29

Y1 - 2007/10/29

N2 - Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous approaches on activity recognition focus on recognition from a single view and ignore the issue of view invariance, and they deal with recognizing a single activity. There are only few published algorithms for segmenting and recognizing complex activities that are composed of more than one activity. In this paper, we present a view invariant human activity recognition approach that uses both motion and shape information. An augmented vector of both optical flow features as well as eigen shape features is used to represent motion and shape of the body in the region of interest in each frame of the sequence. Each activity is represented by a set of hidden Markov models, where each model represents the activity from a different viewing direction, to realize the view invariance. Also, we present a voting-based approach to automatically and effectively segment and recognize complex activities. Experiments on two sets of video clips of different activities show that our method is effective.

AB - Recognizing human activities from image sequences is an active area of research in computer vision. Most of the previous approaches on activity recognition focus on recognition from a single view and ignore the issue of view invariance, and they deal with recognizing a single activity. There are only few published algorithms for segmenting and recognizing complex activities that are composed of more than one activity. In this paper, we present a view invariant human activity recognition approach that uses both motion and shape information. An augmented vector of both optical flow features as well as eigen shape features is used to represent motion and shape of the body in the region of interest in each frame of the sequence. Each activity is represented by a set of hidden Markov models, where each model represents the activity from a different viewing direction, to realize the view invariance. Also, we present a voting-based approach to automatically and effectively segment and recognize complex activities. Experiments on two sets of video clips of different activities show that our method is effective.

KW - Background subtraction

KW - Eigen shape

KW - Fusion

KW - Hidden Markov model

KW - Human activity recognition

KW - View invariance

UR - http://www.scopus.com/inward/record.url?scp=35448934061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35448934061&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:35448934061

VL - 22

SP - 235

EP - 243

JO - International Journal of Robotics and Automation

JF - International Journal of Robotics and Automation

SN - 0826-8185

IS - 3

ER -