E. Belyaev, M. Codreanu, M. Juntti and K. Egiazarian, "Compressive sensed video recovery via iterative thresholding with random transforms," in IET Image Processing, vol. 14, no. 6, pp. 1187-1199, 11 5 2020, doi: 10.1049/iet-ipr.2019.0661
Compressive sensed video recovery via iterative thresholding with random transforms
|Author:||Belyaev, Evgeny1; Codreanu, Marian2; Juntti, Markku3;|
1International Laboratory ”Computer Technologies”, ITMO University, 197101 Saint-Petersburg, Russia
2Department of Science and Technology, Linköping University, 581 83 Linköping, Sweden
3Centre for Wireless Communications, Oulu University, 90014 Oulu, Finland
4Department of Signal Processing, Tampere University, 33720 Tampere, Finland
|Online Access:||PDF Full Text (PDF, 6.3 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2020111390097
Institution of Engineering and Technology,
|Publish Date:|| 2020-11-13
The authors consider the problem of compressive sensed video recovery via iterative thresholding algorithm. Traditionally, it is assumed that some fixed sparsifying transform is applied at each iteration of the algorithm. In order to improve the recovery performance, at each iteration the thresholding could be applied for different transforms in order to obtain several estimates for each pixel. Then the resulting pixel value is computed based on obtained estimates using simple averaging. However, calculation of the estimates leads to significant increase in reconstruction complexity. Therefore, the authors propose a heuristic approach, where at each iteration only one transform is randomly selected from some set of transforms. First, they present simple examples, when block-based 2D discrete cosine transform is used as the sparsifying transform, and show that the random selection of the block size at each iteration significantly outperforms the case when fixed block size is used. Second, building on these simple examples, they apply the proposed approach when video block-matching and 3D filtering (VBM3D) is used for the thresholding and show that the random transform selection within VBM3D allows to improve the recovery performance as compared with the recovery based on VBM3D with fixed transform.
IET image processing
|Pages:||1187 - 1200|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
E.Belyaev acknowledges the support of the Government of the Russian Federation through the ITMO Fellowship and Professorship Program. M. Codreanu would like to acknowledge the support of the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Grant Agreement No. 793402 (COMPRESS NETS). M.Juntti acknowledges the support of Academy of Finland 6Genesis Flagship (grant no. 318927).
|Academy of Finland Grant Number:||
318927 (Academy of Finland Funding decision)
© The Institution of Engineering and Technology 2020. The Definitive Version of Record can be found online at: https://doi.org/10.1049/iet-ipr.2019.0661.