Entity

Time filter

Source Type


Quevedo E.,Oceanic Platform of the Canary Islands | Quevedo E.,Institute for Applied Microelectronics | Sanchez L.,Oceanic Platform of the Canary Islands | Callico G.M.,Oceanic Platform of the Canary Islands | And 3 more authors.
Proceedings of the International Symposium on Consumer Electronics, ISCE | Year: 2013

Super-Resolution (SR) is a set of techniques which objective is to increase and improve the resolution of an image or a video sequence. In this scope, one of the most used techniques is 'fusion', where High-Resolution (HR) images are constructed from several observed Low-Resolution (LR) images. In this paper, a fusion SR algorithm is enhanced introducing an intelligent selective filter which decides the best LR frames to be used in the process. Additionally, an adaptive Macro-Block (MB) size decision maker has been developed to specify an appropriate frame division into MBs. This not only improves the quality but also reduces the computational cost of the baseline algorithm, avoiding the incorporation of non-correlated data. It is also presented how this new algorithm performs well with typical SR applications, such as underwater imagery, surveillance video or remote sensing. The algorithm results are provided on a test environment to objectively compare the quality enhancement of images processed by bilinear interpolation and the two aforementioned methods: Baseline and Enhanced SR, presenting a quantitative comparison based on the PSNR (Peak Signal-to-Noise Ratio) and the SSIM (Structural SIMilarity index). © 2013 IEEE. Source


Guerra R.,Institute for Applied Microelectronics | Santos L.,Institute for Applied Microelectronics | Lopez S.,Institute for Applied Microelectronics | Sarmiento R.,Institute for Applied Microelectronics
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

Linear unmixing of hyperspectral images has rapidly become one of the most widely utilized tools for analyzing the content of hyperspectral images captured by state-of-The-Art remote hyperspectral sensors. The aforementioned unmixing process consists of the following three sequential steps: dimensionality estimation, endmember extraction and abundances computation. Within this procedure, the first two steps are by far the most demanding from a computational point of view, since they involve a large amount of matrix operations. Moreover, the complex nature of these operations seriously difficult the hardware implementation of these two unmixing steps, leading to non-optimized implementations which are not able to satisfy the strict delay requirements imposed by those applications under real-Time or near real-Time requirements. This paper uncovers a new algorithm which is capable of estimating the number of endmembers and extracting them from a given hyperspectral image with at least the same accuracy than state-of-The-Art approaches while demanding a much lower computational effort, with independence of the characteristics of the image under analysis. In particular, the proposed algorithm is based on the concept of orthogonal projections and allows performing the estimation of the number of end-members and their extraction simultaneously, using simple operations, which can be also easily parallelized. In this sense, it is worth to mention that our algorithm does not perform complex matrix operations, such as the inverse of a matrix or the extraction of eigenvalues and eigenvectors, which makes easier its ulterior hardware. The experimental results obtained with synthetic and real hyperspectral images demonstrate that the accuracy obtained with the proposed algorithm when estimating the number of endmembers and extracting them is similar or better than the one provided by well-known state-of-The-Art algorithms, while the complexity of the overall process is significantly reduced. © 2015 SPIE. Source

Discover hidden collaborations