Video scene analysis in 3D wavelet transform domain

Li, Zhi; Liu, Guizhong

doi:10.1007/s11042-010-0594-z

Cited by 4 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the imperfections in the silicon area of the imaging device remain unchanged while a video is being recorded, the video frames should contain an identical PRNU regardless of their different contents. However, because the compression artifacts are highly correlated across the consecutive frames [26] , they can't be removed effectively with the traditional technique by a simple averaging of the 2D noise residuals. In the 3D transform, the filter considers these artifacts as a 3D noise.…”

Section: Proposed Prnu Estimation Approachmentioning

confidence: 99%

“…In the 3D transform, the filter considers these artifacts as a 3D noise. Also, 3D DWT is used since the low-frequency and high frequency coefficients of the 3D DWT could be analysed to obtain more statistical properties of correlation among several successive frames [26].…”

Section: Proposed Prnu Estimation Approachmentioning

confidence: 99%

“…In the rest of the paper, this filter is referred to as the "2D-WWF". Compared to images, videos include highly temporal correlation between frames and the lossy compression artifacts can be very similar in the temporal dimension between adjacent frames [26]. Therefore, the 2D-WWF may not be an efficient approach for video denoising as it relies on simple averaging of the extracted noise residuals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Three Dimensional Denoising Filter For Effective Source Smartphone Video Identification and Verification

Lawgaly

Khelifi

Bouridane

et al. 2022

2022 7th International Conference on Machine Learning Technologies (ICMLT)

View full text Add to dashboard Cite

The field of digital image and video forensics has recently seen significant advances and has attracted attention from a growing number of researchers given the availability of imaging functionalities in most current multimedia devices at no cost including smartphones and tablets. Photo response nonuniformity (PRNU) noise is a sensor pattern noise characterizing the imaging device. However, estimating the PRNU from smartphone videos can be a challenging process because of the lossy compression that digital videos normally undergo for various reasons in addition to other non-unique noise components that interfere with the video data. This paper presents a new filtering technique for PRNU estimation based on the three-dimensional discrete wavelet transform followed by a 3D wiener filter. The rationale is that the 3D filter can filter out the compression artifacts along the temporal dimension in a more effective way than simple averaging. Experimental results on a public video dataset captured by various smartphone devices have shown a significant gain obtained with the proposed approach over the well-known two-dimensional wavelet-based Wiener approach. CCS CONCEPTSSecurity and privacy→Software and application security.

show abstract

Section: Proposed Prnu Estimation Approachmentioning

confidence: 99%

Section: Proposed Prnu Estimation Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Three Dimensional Denoising Filter For Effective Source Smartphone Video Identification and Verification

Lawgaly

Khelifi

Bouridane

et al. 2022

2022 7th International Conference on Machine Learning Technologies (ICMLT)

View full text Add to dashboard Cite

show abstract

“…To avoid time delay and reduce computational problems, a piecewise GMM is presented in [32], while there are still considerable temporal and spatial redundancies left unused. 3D wavelet transform has been applied to detect scene changes in the video sequence in [33]. First, 2D transform of each frame is calculated.…”

Section: Video Content Analysismentioning

confidence: 99%

“…Experimental results show that the Generalized Gaussian Density (GGD) function could yield a suitable estimate of the density of the 2D wavelet coefficients of each subband, using different filters [27,33,[43][44][45]. Minh N. Do used the GGD features and the Kullback-Leibler Distances (KLD) for texture retrieval and gained good results [27].…”

Section: Introductionmentioning

confidence: 99%

Application of 3D-wavelet statistics to video analysis

Omidyeganeh

Ghaemmaghami

Shirmohammadi

2012

Multimed Tools Appl

View full text Add to dashboard Cite

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.

show abstract

Theoretical analysis of constructing wavelet synopsis on partitioned data sets

Kim

2014

Multimed Tools Appl

View full text Add to dashboard Cite

Video scene analysis in 3D wavelet transform domain

Cited by 4 publications

References 27 publications

Three Dimensional Denoising Filter For Effective Source Smartphone Video Identification and Verification

Three Dimensional Denoising Filter For Effective Source Smartphone Video Identification and Verification

Application of 3D-wavelet statistics to video analysis

Theoretical analysis of constructing wavelet synopsis on partitioned data sets

Contact Info

Product

Resources

About