scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Implementation of super-resolution algorithm on FPGA

TL;DR: A FPGA (Field Programmable Gate Array) implementation of super resolution algorithm, which can be resolved up-to 2x, 4x, 8x and 16x image size.
Abstract: Super resolution technique gives an effective way to increase image resolution. Lower resolution is converted into higher resolution. By proposed super resolution algorithm, image is resolved sixteen times. This paper presents a FPGA (Field Programmable Gate Array) implementation of super resolution algorithm. FPGA is used because of its various advantages. In super resolution image size is increased by adopting information from input image itself. Using this algorithm image can be resolved up-to 2x, 4x, 8x and 16x.
Citations
More filters
Proceedings ArticleDOI
01 Oct 2017
TL;DR: This paper proposes an efficient Super-resolution algorithm using overlapping bicubic for hardware implementation and results are verified using processing time and reconstructed images that can be used in real time applications.
Abstract: In practical CCTV applications, there are problems of the camera with low resolution, camera fields of view, and lighting environments. These could degrade the image quality and it is difficult to extract useful information for further processing. Super-resolution techniques have been proposed widely by the researchers. However, many approaches are complex and are difficult to use in practical scenarios. In this paper, we propose an efficient Super-resolution algorithm using overlapping bicubic for hardware implementation. Experimental results are verified using processing time and reconstructed images that can be used in real time applications.

26 citations


Cites background from "Implementation of super-resolution ..."

  • ...Bicubic interpolation was firstly proposed in [1] with several variations to increase the performance in [4, 5]....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: The two key components that are necessary for successful SR restoration are described: the accurate alignment or registration of the LR images and the formulation of an SR estimator that uses a generative image model together with a prior model of the super-resolved image itself.
Abstract: Super-resolution (SR) restoration aims to solve the following problem: given a set of observed images, estimate an image at a higher resolution than is present in any of the individual images. Where the application of this technique differs in computer vision from other fields is in the variety and severity of the registration transformation between the images. In particular this transformation is generally unknown, and a significant component of solving the SR problem in computer vision is the estimation of the transformation. The transformation may have a simple parametric form, or it may be scene dependent and have to be estimated for every point. In either case the transformation is estimated directly and automatically from the images. We describe the two key components that are necessary for successful SR restoration: the accurate alignment or registration of the LR images and the formulation of an SR estimator that uses a generative image model together with a prior model of the super-resolved image itself. As with many other problems in computer vision, these different aspects are tackled in a robust, statistical framework.

296 citations

Journal ArticleDOI
TL;DR: An adaptive self-interpolation algorithm is first proposed to estimate a sharp high-resolution gradient field directly from the input low-resolution image, regarded as a gradient constraint or an edge-preserving constraint to reconstruct the high- resolution image.
Abstract: Super-resolution from a single image plays an important role in many computer vision systems. However, it is still a challenging task, especially in preserving local edge structures. To construct high-resolution images while preserving the sharp edges, an effective edge-directed super-resolution method is presented in this paper. An adaptive self-interpolation algorithm is first proposed to estimate a sharp high-resolution gradient field directly from the input low-resolution image. The obtained high-resolution gradient is then regarded as a gradient constraint or an edge-preserving constraint to reconstruct the high-resolution image. Extensive results have shown both qualitatively and quantitatively that the proposed method can produce convincing super-resolution images containing complex and sharp features, as compared with the other state-of-the-art super-resolution algorithms.

158 citations

Journal ArticleDOI
TL;DR: A novel example-based single-image superresolution procedure that upscales to high-resolution (HR) a given low-resolution input image without relying on an external dictionary of image examples, which turns out to give the best performance when considering objective metrics.
Abstract: This paper presents a novel example-based single-image superresolution procedure that upscales to high-resolution (HR) a given low-resolution (LR) input image without relying on an external dictionary of image examples. The dictionary instead is built from the LR input image itself, by generating a double pyramid of recursively scaled, and subsequently interpolated, images, from which self-examples are extracted. The upscaling procedure is multipass, i.e., the output image is constructed by means of gradual increases, and consists in learning special linear mapping functions on this double pyramid, as many as the number of patches in the current image to upscale. More precisely, for each LR patch, similar self-examples are found, and, because of them, a linear function is learned to directly map it into its HR version. Iterative back projection is also employed to ensure consistency at each pass of the procedure. Extensive experiments and comparisons with other state-of-the-art methods, based both on external and internal dictionaries, show that our algorithm can produce visually pleasant upscalings, with sharp edges and well reconstructed details. Moreover, when considering objective metrics, such as Peak signal-to-noise ratio and Structural similarity, our method turns out to give the best performance.

89 citations


"Implementation of super-resolution ..." refers methods in this paper

  • ...Marco Bevilacqua, et al [3], has used a dictionary for SR....

    [...]

Journal ArticleDOI
TL;DR: In this article, an iterative reweighted method is proposed to estimate the unknown parameters and the sparse signals in a continuous domain by iteratively decreasing a surrogate function majorizing a given objective function, which results in a gradual and interweaved iterative process.
Abstract: In many practical applications such as direction-of- arrival (DOA) estimation and line spectral estimation, the sparsifying dictionary is usually characterized by a set of unknown parameters in a continuous domain. To apply the conventional compressed sensing to such applications, the continuous parameter space has to be discretized to a finite set of grid points. Discretization, however, incurs errors and leads to deteriorated recovery performance. To address this issue, we propose an iterative reweighted method which jointly estimates the unknown parameters and the sparse signals. Specifically, the proposed algorithm is developed by iteratively decreasing a surrogate function majorizing a given objective function, which results in a gradual and interweaved iterative process to refine the unknown parameters and the sparse signal. Numerical results show that the algorithm provides superior performance in resolving closely-spaced frequency components.

68 citations

Journal ArticleDOI
TL;DR: An adaptive algorithm is proposed in this paper to integrate a higher level image classification task and a lower level super-resolution process, in which it incorporate reconstruction-based super- resolution algorithms, single-image enhancement, and image/video classification into a single comprehensive framework.
Abstract: Super-resolution technology provides an effective way to increase image resolution by incorporating additional information from successive input images or training samples. Various super-resolution algorithms have been proposed based on different assumptions, and their relative performances can differ in regions of different characteristics within a single image. Based on this observation, an adaptive algorithm is proposed in this paper to integrate a higher level image classification task and a lower level super-resolution process, in which we incorporate reconstruction-based super-resolution algorithms, single-image enhancement, and image/video classification into a single comprehensive framework. The target high-resolution image plane is divided into adaptive-sized blocks, and different suitable super-resolution algorithms are automatically selected for the blocks. Then, a deblocking process is applied to reduce block edge artifacts. A new benchmark is also utilized to measure the performance of super-resolution algorithms. Experimental results with real-life videos indicate encouraging improvements with our method.

58 citations


"Implementation of super-resolution ..." refers methods in this paper

  • ...Heng Su, et al [1] discussed an adaptive block based Super Resolution (SR) technique....

    [...]