Block Matching Video Compression Based on Sparse Representation and Dictionary Learning

Irannejad, Maziar; Mahdavi-Nasab, Homayoun

doi:10.1007/s00034-017-0720-5

Cited by 5 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the ODL is a special case of the RLS-DLA used in the proposed schemes with a fixed forgetting factor equal to one. More complex hybrid SR-based VC schemes of [19] and [22] achieve higher R-D results as expected. The added interframe information and super-resolution technique used in [19] results in up to 2 dB higher qualities compared with the H.264.…”

Section: Computational Complexity and Comparisonsupporting

confidence: 76%

“…In our previous works, a hybrid intraframe and interframe sparse VC based on overcomplete DL is proposed in [22], which validates the advantages of sparse coding compared to H.264/AVC and even HEVC for low bitrates. The low bitrate SNR scalable VC based on overcomplete DL proposed in [23] also shows better performance than current scalable VC standards using complete dictionaries.…”

Section: Introductionsupporting

confidence: 61%

“…The added interframe information and super‐resolution technique used in [19] results in up to 2 dB higher qualities compared with the H.264. And even superior results are reported in [22] compared to the H.264 and HEVC at low bitrates. However, being hybrid methods and using excessive time‐consuming techniques such as the full search motion estimation of [22] hinder reasonable comparisons and result in much more running‐times.…”

Section: Resultsmentioning

confidence: 99%

“…And even superior results are reported in [22] compared to the H.264 and HEVC at low bitrates. However, being hybrid methods and using excessive time‐consuming techniques such as the full search motion estimation of [22] hinder reasonable comparisons and result in much more running‐times. As seen in Table 6, this is about three to five times for [22] compared to the SISC2, and even more for [19], though using CIF formats.…”

Section: Resultsmentioning

confidence: 99%

“…It employs an online DL (ODL) method which is trained and updated using the video being coded. The results reveal the superior performance of the VC compared with the H264-Intra FIGURE 11 R-D performance of the two proposed semi-intraframe VC methods compared to the basic intraframe and the interframe VC based on the RLS-DLA [22] and the K-SVD trained on the video under compression with about 0.4 to 4 dB higher PSNRs for the former and 0.5 dB on average, using the CIF tested sequences at low bitrates. There were no comparisons with the HEVC and no run-times reported for the coding process.…”

Section: Computational Complexity and Comparisonmentioning

confidence: 96%

See 4 more Smart Citations

Sparse representation based intraframe and semi‐intraframe video coding schemes for low bitrates

Irannejad

Mahdavi-Nasab

2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

This paper proposes some extensions of the successful sparse coding of still images to intraframe and semi-intraframe video coding. The presented frameworks apply the efficient K-singular value decomposition and recursive least squares dictionary learning methods for sparse representation of videos to study their coding performances. In the proposed semi-intraframe schemes, namely, SISC1 and SISC2, only frame-blocks with more than a threshold deviation from the blocks of the previous frame are transmitted/coded. This reduces the required bitrate and prevents the sparse coding of similar blocks, leading to more efficient video coding methods. The results show that the dictionary learning-based intraframe coding improves the rate-distortion performance of the conventional Motion-JPEG and Motion-JPEG2000 at low bitrates for more than about 3 and 0.5 dB of PSNR on average (for 0.2-1 bpp compression), respectively. The proposed methods outperform the basic dictionary learning-based coding, especially for slower changing videos, generally, with more than 3 dB superiority on average over the tested bitrates. These schemes even present superior performance than the HEVC in the intramode for the complex textured or cluttered scenes. The proposed SISC2 method also saves up to about 50% of the sparse coding computational cost by preventing the coding of more similar frame-blocks. 1 This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Computational Complexity and Comparisonsupporting

confidence: 76%

Section: Introductionsupporting

confidence: 61%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Computational Complexity and Comparisonmentioning

confidence: 96%

See 3 more Smart Citations

Sparse representation based intraframe and semi‐intraframe video coding schemes for low bitrates

Irannejad

Mahdavi-Nasab

2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

Low bit-rate SNR scalable video coding based on overcomplete dictionary learning and sparse representation

Irannejad

Mahdavi-Nasab

2019

Multidim Syst Sign Process

View full text Add to dashboard Cite

3D Tensor Auto-encoder with Application to Video Compression

Li¹,

Liu

Sun

et al. 2021

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Auto-encoder has been widely used to compress high-dimensional data such as the images and videos. However, the traditional auto-encoder network needs to store a large number of parameters. Namely, when the input data is of dimension n , the number of parameters in an auto-encoder is in general O ( n ). In this article, we introduce a network structure called 3D Tensor Auto-Encoder (3DTAE). Unlike the traditional auto-encoder, in which a video is represented as a vector, our 3DTAE considers videos as 3D tensors to directly pass tensor objects through the network. The weights of each layer are represented by three small matrices, and thus the number of parameters in 3DTAE is just O ( n 1/3). The compact nature of 3DTAE fits well the needs of video compression. Given an ensemble of high-dimensional videos, we represent them as 3DTAE networks plus some small core tensors, and we further quantize the network parameters and the core tensors to get the final compressed data. Experimental results verify the efficiency of 3DTAE.

show abstract

Block Matching Video Compression Based on Sparse Representation and Dictionary Learning

Cited by 5 publications

References 41 publications

Sparse representation based intraframe and semi‐intraframe video coding schemes for low bitrates

Sparse representation based intraframe and semi‐intraframe video coding schemes for low bitrates

Low bit-rate SNR scalable video coding based on overcomplete dictionary learning and sparse representation

3D Tensor Auto-encoder with Application to Video Compression

Contact Info

Product

Resources

About