Abstract
Video super-resolution is a technique which generates a high-resolution video sequence from multiple low-resolution frames. This paper presents a novel algorithm for video super-resolution (NA-VSR) to improve the resolution quality of the image as well as video. This method consists of a combination of interpolation and image enhancement. The bicubic interpolation has been employed to increase the pixel density and luminance compensation is used to get the super-resolved view of the interpolated frame. The algorithm is designed in MATLAB 2016 and quality of the image is estimated with design metrics like Peak signal-to-noise ratio (PSNR) and Structural Similarity index method (SSIM). Experimental results show that the quality of output high-resolution video of NA-VSR method is good as compared to previously published methods like Bicubic, SRCNN, and ASDS. PSNR of the proposed method is improved by 7.84 dB, 6.92 dB, and 7.42 dB as compared to Bicubic, SRCNN, and ASDS, respectively.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
