Video super-resolution with registration-reliability regulation and adaptive total variation

Zhang, Xinfeng; Xiong, Ruiqin; Ma, Siwei; Li, Ge; Gao, Wen

doi:10.1016/j.jvcir.2015.04.002

Cited by 13 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, video enhancement aims at improving the clarity of the input Video enhancement is performed based on the spatial domain and frequency domain. In the spatial domain, the pixels are manipulated directly in the space plain, and in the frequency domain, the spatial frequency spectrum of the image is modified [11]. Even though video enhancement derives high quality videos, there are some degradation factors affecting the quality enhancement process.…”

Section: Introductionmentioning

confidence: 99%

“…The aim of the video SR is to generate the High-Resolution (HR) video frames using the sequence of Low-Resolution (LR) inputs. Video superresolution drags a lot of attention in the last few years both on the academic side and on the industry [10] [11]. The available HR video devices are highly expensive to generate, store and transmit the HR videos and hence, the demand falls on the modern SR techniques such that the generation of the HR videos from LR ones is facilitated [3].…”

Section: Introductionmentioning

confidence: 99%

“…Video SR techniques enable us to perform the video coding/decoding [14], face video hallucination [15], video surveillance systems [16], remote sensing systems [17], medical image analysis [18] and stereoscopic video processing [19] [11] [4]. SR techniques are grouped into two main categories, such as single-image based and multi-frame based [20], [21].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid SVR-ACNN model: Proposed Video Super-Resolution method for video enhancement

M.¹

2019

Journal of Digital Information Management

View full text Add to dashboard Cite

Video super-resolution techniques are the need of the hour for the high-resolution display devices as the current high-resolution videos are the basic question. Even though there are a large number of techniques employed for the video super-resolution, all these existing techniques face a hectic challenge at various conditions. Thus, this paper proposes an effective video resolution strategy using the hybrid Support vector regression-Actor Critic Neural Network (SVR-ACNN) model for video enhancement. The super-resolution images formed using the individual SVR model and Actor Critic Neural Network are integrated using the weighted average concept. The Actor Critic Neural Network is tuned optimally using the proposed Fractional-based Sine Cosine algorithm (F-SCA) that is responsible for the global optimal convergence. The experimentation of the proposed method utilizes three videos taken from the Cambridgedriving Labeled Video Database (CamVid), and the results are analyzed for three scaling factors. The outcome of the analysis proves that the proposed method offers a better super-resolution image with a better PSNR, SSIM, and SDME of 33.6447dB, 0.9398, and 45.2779, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%