Application of 3D-wavelet statistics to video analysis

Video activity analysis is used in various video applications such as human action recognition, video retrieval, video archiving. In this paper, we propose to apply 3D wavelet transform statistics to natural video signals and employ the resulting statistical attributes for video modeling and analysi...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2013-08, Vol.65 (3), p.441-465
Main Authors: Omidyeganeh, M., Ghaemmaghami, S., Shirmohammadi, S.
Format: Article
Language:English
Subjects:
3-D graphics
Applied sciences
Archiving
Artificial intelligence
Classification
Computer Communication Networks
Computer Science
Computer science
control theory
systems
Data processing. List processing. Character string processing
Data Structures and Information Theory
Density
Efficiency
Exact sciences and technology
Human
Information systems. Data bases
Mathematical models
Memory organisation. Data processing
Methods
Multimedia Information Systems
Pattern recognition. Digital image processing. Computational geometry
Software
Special Purpose and Application-Based Systems
Statistics
Studies
Support vector machines
Three dimensional
Time series
Video compression
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video activity analysis is used in various video applications such as human action recognition, video retrieval, video archiving. In this paper, we propose to apply 3D wavelet transform statistics to natural video signals and employ the resulting statistical attributes for video modeling and analysis. From the 3D wavelet transform, we investigate the marginal and joint statistics as well as the Mutual Information (MI) estimates. We show that marginal histograms are approximated quite well by Generalized Gaussian Density (GGD) functions; and the MI between coefficients decreases when the activity level increases in videos. Joint statistics attributes are applied to scene activity grouping, leading to 87.3% accurate grouping of videos. Also, marginal and joint statistics features extracted from the video are used for human action classification employing Support Vector Machine (SVM) classifiers and 93.4% of the human activities are properly classified.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-012-1012-5