GPU accelerated video super resolution using transformed spatio-temporal exemplars Online publication date: Fri, 19-Jul-2019
by Chaitanya Pavan Tanay Kondapalli; Srikanth Khanna; Venkatachalam Chandrasekaran; Pallav Kumar Baruah; Diwakar Kartheek Pingali; Sai Hareesh Anamandra
International Journal of Grid and Utility Computing (IJGUC), Vol. 10, No. 4, 2019
Abstract: Super-resolution (SR) is the method of obtaining high-resolution (HR) images or image sequences from one or more low-resolution (LR) images of a scene. Huang et al. in 2015 proposed a transformed self-exemplar internal database technique which takes advantage of fractal nature in an image by expanding patch search space using geometric variations. This method fails if there is no patch redundancy within and across image scales and also if there is a failure in detecting vanishing points (VP) which are used to determine perspective transformation between LR image and its sub-sampled form. In this paper, we expand the patch search space by taking advantage of temporal dimension of image frames in the scene video and also use an efficient vanishing point (VP) detection technique by Lezama et al. in 2014 and are thereby able to successfully super-resolve even the failure cases of Huang et al. and an overall improvement in PSNR. We also focused on reducing the computation time by exploiting the embarrassingly parallel nature of the algorithm. We achieved a speedup of six on multi-core, up to 11 on GPU, around 16 on hybrid platform of multi-core and GPU by parallelising the proposed algorithm. Using our hybrid implementation, we achieved 32x super-resolution factor in limited time.
Online publication date: Fri, 19-Jul-2019
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Grid and Utility Computing (IJGUC):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email email@example.com