Gustavo Callico | Universidad de Las Palmas de Gran Canaria (original) (raw)

Papers by Gustavo Callico

This paper presents a new strategy in order to accelerate the execution of sequential endmember e... more This paper presents a new strategy in order to accelerate the execution of sequential endmember extraction algorithms without compromising their performance in terms of the accuracy of the estimated endmembers. In particular, our proposal takes advantage of the correlation between pixels located in adjacent spatial positions as well as of the information provided by the dimensionality reduction step that takes place priors to the endmember extraction itself. The results demonstrate that when the proposed strategy is applied to the well-known Vertex Component Analysis (VCA) sequential algorithm, almost half of the computing time is saved with negligible variations in the quality of the endmembers extracted. Moreover, this is achieved with independence of the amount of noise and/or the number of endmembers of the hyperspectral image under processing.

Electronics, Dec 6, 2019

Currently, high-level synthesis (HLS) methods and tools are a highly relevant area in the strateg... more Currently, high-level synthesis (HLS) methods and tools are a highly relevant area in the strategy of several leading companies in the field of system-on-chips (SoCs) and field programmable gate arrays (FPGAs). HLS facilitates the work of system developers, who benefit from integrated and automated design workflows, considerably reducing the design time. Although many advances have been made in this research field, there are still some uncertainties about the quality and performance of the designs generated with the use of HLS methodologies. In this paper, we propose an optimization of the HLS methodology by code refactoring using Xilinx SDSoC TM (Software-Defined System-On-Chip). Several options were analyzed for each alternative through code refactoring of a multiclass support vector machine (SVM) classifier written in C, using two different Zynq ® -7000 SoC devices from Xilinx, the ZC7020 (ZedBoard) and the ZC7045 (ZC706). The classifier was evaluated using a brain cancer database of hyperspectral images. The proposed methodology not only reduces the required resources using less than 20% of the FPGA, but also reduces the power consumption -23% compared to the full implementation. The speedup obtained of 2.86× (ZC7045) is the highest found in the literature for SVM hardware implementations.

Sensors, Jul 17, 2018

The use of hyperspectral imaging (HSI) in the medical field is an emerging approach to assist phy... more The use of hyperspectral imaging (HSI) in the medical field is an emerging approach to assist physicians in diagnostic or surgical guidance tasks. However, HSI data processing involves very high computational requirements due to the huge amount of information captured by the sensors. One of the stages with higher computational load is the K-Nearest Neighbors (KNN) filtering algorithm. The main goal of this study is to optimize and parallelize the KNN algorithm by exploiting the GPU technology to obtain real-time processing during brain cancer surgical procedures. This parallel version of the KNN performs the neighbor filtering of a classification map (obtained from a supervised classifier), evaluating the different classes simultaneously. The undertaken optimizations and the computational capabilities of the GPU device throw a speedup up to 66.18× when compared to a sequential implementation.

An Efficient Architecture for Hardware Implementation of H.264/AVC Deblocking Filtering

2008 Second International Conference on Electrical Engineering, 2008

Abstract In this paper, a novel hardware architecture for real-time implementation of the adaptiv... more Abstract In this paper, a novel hardware architecture for real-time implementation of the adaptive deblocking filtering process specified by the H. 264/AVC standard, is presented. The proposed architecture is based on a double-filter strategy that results in a significant ...

HLS code refactoring using SDSoC applied to multiclass SVM classification of Hyperspectral Images

Analysis of the transaction of data for a scalable video decoder

It is highly desirable to know in advance the transaction of data in the design of any electronic... more It is highly desirable to know in advance the transaction of data in the design of any electronic embedded system. It is of especial interest for data-intensive applications, such as complex video systems, when the options available in the video decoder continuously change and/or the features of the input video sequences are different. This paper exposes the development of a profiling tool intended to assist the designer on the decision making based on the transaction of data during the decoding of video sequences using the H.264 Scalable Video Coding (SVC) standard. The tool incorporates some Python scripts that allow the designer to analyze the data transaction in the video decoder, with several automatic profiling utilities for the management of bitstreams and decoding tasks. Using the profiling scripts, the results show that the data transaction load changes based on the intrinsic characteristics of the video sequence and on the scalable options selected. Due to the huge number of functions that form part of the SVC video decoder, a set of modules that better describe the internal structure of the decoder has been defined. The allocation of functions to modules is open to the designer and can be changed at any time to accommodate changes in the system. This environment allows the system designer to make better decisions about the load distribution of data transactions, based on the modules defined inside the tool to create the profile.

On the use of ritz values for calculating the number of endmembers in hyperspectral images

Signal subspace identification is a crucial step in many hyperspectral processing algorithms such... more Signal subspace identification is a crucial step in many hyperspectral processing algorithms such as target detection, change detection, classification, and unmixing. This is due to the fact that a correct dimensionality reduction improves algorithm performances and reduces their complexity and data requirements. This paper introduces a new method for this task which is based on the Ritz values obtained in methods such as the restarted Arnoldi method or the Lanczos method for calculating the eigenvalues and eigenvectors of a given matrix. In particular, it first calculates a high number of eigenvalues and eigenvectors, and a Ritz value per eigenvalue calculated and then, it estimates the dimension of the signal subspace according to the Ritz values obtained. The results obtained with the proposed method for synthetic and real hyperspectral images verify the performance of the introduced methodology to estimate the number of endmembers in different types of hyperspectral images. Moreover, these results are better than the ones obtained, for the same images, with the most popular algorithm for this task in the state of the art, i.e. the HySIME and the Virtual Dimensionality algorithms.

A novel method to estimate the number of endmembers in hyperspectral images based on the virtual dimensionality concept

This paper presents a modification of the Harsanyi-Farrand-Chang (HFC) method to automatically es... more This paper presents a modification of the Harsanyi-Farrand-Chang (HFC) method to automatically estimate the number of endmembers of hyperspectral images when assuming a linear mixing model. The proposed unsupervised algorithm dynamically determines the probability of false alarm required as an input of the HFC method, with independence of the amount of noise, spatial dimensions, and/or the real number of endmembers of the hyperspectral image under processing. The Automatic HFC (A-HFC) method has been tested using synthetic and real hyperspectral images, demonstrating in all the cases an equal or superior performance than HFC in terms of precision when computing the number of endmembers. Additionally, for the real image Cuprite, the number of endmembers coincides with the number of endmembers obtained with the HFC method and it is similar to the one given by the hyperspectral subspace identification method (HySime), which definitely confirms the accuracy of the proposed method.

Optics Communications, Dec 1, 2017

Image spatial resolution is critical in several fields such as medicine, communications or satell... more Image spatial resolution is critical in several fields such as medicine, communications or satellite, and underwater applications. While a large variety of techniques for image restoration and enhancement has been proposed in the literature, this paper focuses on a novel Super-Resolution fusion algorithm based on a Multi-Camera environment that permits to enhance the quality of underwater video sequences without significantly increasing computation. In order to compare the quality enhancement, two objective quality metrics have been used: PSNR (Peak Signal-to-Noise Ratio) and the SSIM (Structural SIMilarity) index. Results have shown that the proposed method enhances the objective quality of several underwater sequences, avoiding the appearance of undesirable artifacts, with respect to basic fusion Super-Resolution algorithms.

Zenodo (CERN European Organization for Nuclear Research), Sep 25, 2022

arXiv (Cornell University), Oct 25, 2007

Motion estimation is the most critical process in video coding systems. First of all, it has a de... more Motion estimation is the most critical process in video coding systems. First of all, it has a definitive impact on the rate-distortion performance given by the video encoder. Secondly, it is the most computationally intensive process within the encoding loop. For these reasons, the design of high-performance low-cost motion estimators is a crucial task in the video compression field. An adaptive cost block matching (ACBM) motion estimation technique is presented in this paper, featuring an excellent tradeoff between the quality of the reconstructed video sequences and the computational effort. Simulation results demonstrate that the ACBM algorithm achieves a slight better rate-distortion performance than the one given by the well-known full search algorithm block matching algorithm with reductions of up to 95% in the computational load.

Sensors

Hyperspectral Imaging (HSI) is increasingly adopted in medical applications for the usefulness of... more Hyperspectral Imaging (HSI) is increasingly adopted in medical applications for the usefulness of understanding the spectral signature of specific organic and non-organic elements. The acquisition of such images is a complex task, and the commercial sensors that can measure such images is scarce down to the point that some of them have limited spatial resolution in the bands of interest. This work proposes an approach to enhance the spatial resolution of hyperspectral histology samples using super-resolution. As the data volume associated to HSI has always been an inconvenience for the image processing in practical terms, this work proposes a relatively low computationally intensive algorithm. Using multiple images of the same scene taken in a controlled environment (hyperspectral microscopic system) with sub-pixel shifts between them, the proposed algorithm can effectively enhance the spatial resolution of the sensor while maintaining the spectral signature of the pixels, competing...

Sensors, 2022

Hyperspectral Imaging (HSI) techniques have demonstrated potential to provide useful information ... more Hyperspectral Imaging (HSI) techniques have demonstrated potential to provide useful information in a broad set of applications in different domains, from precision agriculture to environmental science. A first step in the preparation of the algorithms to be employed outdoors starts at a laboratory level, capturing a high amount of samples to be analysed and processed in order to extract the necessary information about the spectral characteristics of the studied samples in the most precise way. In this article, a custom-made scanning system for hyperspectral image acquisition is described. Commercially available components have been carefully selected in order to be integrated into a flexible infrastructure able to obtain data from any Generic Interface for Cameras (GenICam) compliant devices using the gigabyte Ethernet interface. The entire setup has been tested using the Specim FX hyperspectral series (FX10 and FX17) and a Graphical User Interface (GUI) has been developed in order...

Libro de Actas IN-RED 2020: VI Congreso de Innovación Edicativa y Docencia en Red, 2020

The implementation of robotics in schools is inevitable in the years to come. Currently, this int... more The implementation of robotics in schools is inevitable in the years to come. Currently, this integration is not feasible for all schools (especially public ones) due to the high economic cost, which in most cases offer a closed system (both hardware and software) which limits the robot to a single educational level. The educational innovation project "ROBOT-EDULPGC, Design, implementation and implementation of a low-cost modular educational robotics platform" of the University of Las Palmas de Gran Canaria, seeks to offer an educational platform designed for use at all educational levels (multidisciplinary), with free hardware and software, and low cost, thus eliminating the economic barrier. This work reflects the results of a statistical study carried out on students of different engineering degrees, in particular those of the Degree in Industrial and Automatic Electronic Engineering, all belonging to the School of Industrial and Civil Engineering at the University of L...

Expectativas del profesorado en la implementación curricular de una plataforma modular de robótica educativa

Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling, 2019

Brain cancer surgery has the goal of performing an accurate resection of the tumor and preserving... more Brain cancer surgery has the goal of performing an accurate resection of the tumor and preserving as much as possible the quality of life of the patient. There is a clinical need to develop non-invasive techniques that can provide reliable assistance for tumor resection in real-time during surgical procedures. Hyperspectral imaging (HSI) arises as a new, noninvasive and non-ionizing technique that can assist neurosurgeons during this difficult task. In this paper, we explore the use of deep learning (DL) techniques for processing hyperspectral (HS) images of in-vivo human brain tissue. We developed a surgical aid visualization system capable of offering guidance to the operating surgeon to achieve a successful and accurate tumor resection. The employed HS database is composed of 26 in-vivo hypercubes from 16 different human patients, among which 258,810 labelled pixels were used for evaluation. The proposed DL methods achieve an overall accuracy of 95% and 85% for binary and multiclass classifications, respectively. The proposed visualization system is able to generate a classification map that is formed by the combination of the DL map and an unsupervised clustering via a majority voting algorithm. This map can be adjusted by the operating surgeon to find the suitable configuration for the current situation during the surgical procedure.

$Research paper thumbnail of Processing diffraction-limited images through innovative Super-Resolution techniques$

Proceedings of the Adaptive Optics for Extremely Large Telescopes 5, 2017

In the ELTs era, where the need for versatile and innovative solutions to produce very high spati... more In the ELTs era, where the need for versatile and innovative solutions to produce very high spatial resolution images has become a major issue, the search of synergies with other science fields seems a logic step. One of the considered alternatives to reach high-resolution images is the use of several frames of the same target, this approach is known as fusion Super-Resolution in the state of the art. Here, we propose the use of the super-resolution techniques based on structural similarity and initially developed for submarine environments. 1 Accordingly, innovative algorithms are implemented in order to process the science images from an Adaptive Optics system to obtain diffraction-limited images in the optical wavelengths.

Sensors, 2018

The work presented in this paper is focused on the use of spectroscopy to identify the type of ti... more The work presented in this paper is focused on the use of spectroscopy to identify the type of tissue of human brain samples employing support vector machine classifiers. Two different spectrometers were used to acquire infrared spectroscopic signatures in the wavenumber range between 1200–3500 cm−1. An extensive analysis was performed to find the optimal configuration for a support vector machine classifier and determine the most relevant regions of the spectra for this particular application. The results demonstrate that the developed algorithm is robust enough to classify the infrared spectroscopic data of human brain tissue at three different discrimination levels.

System level methodology based on VIPPE applied to the implementation of a scalable video decoder on the ZynQ platform

2015 Conference on Design of Circuits and Integrated Systems (DCIS), 2015

One of the first problems that a hardware designer needs to solve when facing a new and complex e... more One of the first problems that a hardware designer needs to solve when facing a new and complex electronic design, is to know in advance where the critical parts of the design are, and how many resources the design will require. This information will ease the developing of feasible systems and will help in the design of well suited architectures. The Open SVC (Scalable Video Coding) Decoder (OSD) is an open source system created at IETR/INSA at Rennes that implements a SV decoder written in language. The scalable video encoder supposes an important overload compared with its counterpart non-scalable video encoder, which inherently already exhibits a very high computational load. Due to the huge number of functions that form part of the SV video decoder, a set of internal modules that better describes the internal structure of the decoder has been defined. In this scenario, two aspects have been selected to be the critical ones: the computational load and the transaction of data. In order to adopt appropriate decisions related with the system implementation.. This paper presents a methodology based on VIPPE that will be used to perform the profiling of a complex system like the OSD over a user-defined platform, the ZynQ from Xilinx in this case, composed by two ARM cores and an FPGA. The profiling results will guided the implementation of the OSD on the aforementioned ZynQ platform. The methodology can be easily extrapolated to any other complex design.

Super-resolution with adaptive macro-block topology applied to a multi-camera system

IEEE Transactions on Consumer Electronics, 2015

ABSTRACT