Loading...

Application of 3D-wavelet statistics to video analysis

Omidyeganeh, M ; Sharif University of Technology | 2013

878 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/s11042-012-1012-5
  3. Publisher: 2013
  4. Abstract:
  5. 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
  6. Keywords:
  7. 3D wavelet transform statistics ; 3-D wavelet transforms ; Generalized Gaussian density ; Human action classifications ; Human-action recognition ; Mutual informations ; Video analysis ; Video applications ; Wavelet statistics ; Gesture recognition ; Image retrieval ; Statistics ; Support vector machines ; Wavelet transforms ; Three dimensional computer graphics
  8. Source: Multimedia Tools and Applications ; Volume 65, Issue 3 , 2013 , Pages 441-465 ; 13807501 (ISSN)
  9. URL: http://link.springer.com/article/10.1007%2Fs11042-012-1012-5