STRATUM is a Horizon Europe multi-partner project developing a clinically validated, real-time 3D decision support tool for brain tumour surgery. The system integrates Hyperspectral Imaging (HSI), AI-based multimodal data fusion, and heterogeneous High-Performance Computing (HPC) architectures combining Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), and Processing-In-Memory (PIM) technologies. A touchless augmented reality interface facilitates safe and intuitive intraoperative interaction. The distinguishing characteristic of STRATUM is its end-to-end co-designed approach, which integrates advanced computing, state-of-the-art imaging and clinical expertise into a unified Point-of-Care (PoC) platform. Utilising a structured co-creation methodology involving surgeons, engineers, and social scientists, the project ensures usability, safety and regulatory compliance from its early design stages to its clinical validation. The usability of STRATUM will be tested in three hospitals located in different European regions with diverse conditions and regulations. This will allow to collect advice and remarks from surgical staff in a continuous co-creation and co-tuning protocol. Beyond its clinical objectives, STRATUM contributes to the advancement of heterogeneous computing for real-time diagnostics, AI acceleration in critical medical environments and energy-efficient system integration. Furthermore, it delivers open datasets, validated AI pipelines, and performance benchmarks with a view to fostering future research and industrial innovation in digital surgery. The STRATUM project establishes a replicable model for intelligent, human-centred computing integrating microelectronics, AI and medicine.The paper presents an overview of the project in terms of aims, concepts and technologies and the description of the state of the work when approaching the end of the second of the five years planned. Specifically, the outcomes of the steps related to the collaboration with surgeons and medical staff (co-creation process) and the intelligent Graphical User Interface (GUI) development will be described. The latter allows for contactless interaction of the surgeon with several functions that have already been developed in the system.

Hyperspectral (HS) imaging systems are currently widely used in biomedical research for developing new diagnostic tools that could help clinicians to improve accuracy in diagnostic tasks. These HS systems are commonly expensive and for certain medical applications they capture redundant information not needed for the application at hand. Hence, research for developing low-cost HS or Multispectral (MS) acquisitions systems is demanded by the medical instrumentation industry. In this study, a MS imaging system based on Light Emitting Diode (LED) technology has been designed and validated. To achieve this, an Arduino UNO microcontroller, a 4-to-16 demultiplexer, and a set of modular control circuit boards has been utilized for LED control, along with a ring structure to house the set of selected narrow band LEDs. Several tests have been conducted to validate the spectral response of the system by using a calibrated polymer as reference, demonstrating the potential of the proposed approach to develop customized LED-based MS systems.

Multimodal images (MIs) can capture different modalities of a scene with multiple applications in medicine, remote sensing, food inspection, among others. Over a 2D domain, these images acquire spectral/morphological/temporal information of each spatial point. Unmixing methodologies can decompose this spatial and spectral/morphological/temporal information. In this letter, a unified framework is proposed for unsupervised unmixing, explicitly accounting for Gaussian and sparse noise. Our approach is novel in three key aspects: (i) addresses the general case of multimodal images, (ii) unifies linear and multilinear mixing models, and (iii) incorporates noise effects into the synthesis schemes. The proposed methodology relies on cyclic coordinate descent optimization (CCDO), constrained quadratic estimation, and L1-regularization. For the validation stage, two types of synthetic MIs were used with additive Gaussian and sparse noise terms. Additionally, the Urban dataset was employed for further validation to consider a real-world scenario. The results show that the proposed methodologies provide accurate reconstructions of the datasets, as well as the ground-truth abundance maps and end-members with low computational time.

This work presents a Field-Programmable Gate Array (FPGA) implementation of a U-Net-based model for heart sound segmentation, building on previous hardware optimization efforts. By converting model parameters to Read-Only Memories instead of Advanced eXtensible Interface (AXI) ports, Block Random Access Memory consumption decreased significantly, from 99% to 58%. Additionally, latency was reduced from 29.27 to 17.66 ms as estimated during High-Level Synthesis (HLS) cosimulation. The U-Net block was integrated into a block design, connected to the Zynq Processing System, facilitating model evaluation on the PYNQ-Z2 board. Model accuracy reached 91.14%, close to HLS C simulation results and high-level Python description. FPGA measured latency was 17.77±0.01 ms, achieving real-time performance, with power consumption estimated at 134±14 mW. Energy per inference was calculated at 2.38±0.07 mJ. A power reduction study showed a 22 % decrease in minimum power consumption compared to default settings, but no significant reduction in energy consumption was observed. This study offers insights for future optimizations, highlighting the applicability of FPGA-based heart sound segmentation in real-world scenarios, and setting the specifications for a potential hand-held device based on this design.

Integrated digital diagnostics can support complex surgical procedures in many anatomical sites, brain tumour surgery being the most complex. STRATUM is a 5-year Horizon Europe funded project with the goal of developing an innovative 3D decision support tool for brain tumour surgeries, based on real-time multimodal data processing using artificial intelligence algorithms. The proposed tool is envisioned as an energy-efficient Point-of-Care computing system to be integrated within neurosurgical workflows to aid surgeons to make informed, efficient, and accurate decisions during surgical procedures. The expected long-term impact of STRATUM is to reduce the duration of surgical procedures, thus decreasing patients' risks, but also optimising the resources of European health care systems.

Hyperspectral Imaging (HSI) is a novel non-invasive, label-free technique for rapid medical diagnosis, capable of capturing a wide range of the electromagnetic spectrum in numerous narrow spectral bands. This comprehensive data acquisition poses challenges in clinical settings due to patient movement (e.g., breathing, tremors, heartbeat). This work presents a method to compensate inter-band movements during HSI acquisition using spectral scanning acquisition systems. The system used in this work is based on a Liquid Crystal Tunable Filter (LCTF), featuring a Kurios VBl filter (Thorlabs, USA) and a CSl35 MUN monochrome camera, capturing the visible range (420–730 nm) in successive frames at different wavelengths. The proposed method uses iterative image registration to align each frame with the initial reference frame, correcting for movements along the x-axis, y-axis, and rotational shifts. The system's efficacy was validated using two datasets: static and dynamic. In the first one, the HS images were captured with no motion applied and later they were digitally deformed. The second dataset was acquired employing a custom motion platform. Results show improved alignment and reduced motion artifacts in the resulting HS images, highlighting the potential of the proposed method to improve the reliability of HSI in clinical applications.

Hyperspectral imaging (HSI) has gained prominence in medical diagnostics due to its ability to capture and analyse detailed spectral information beyond human visual capabilities. Processing of HSI data is essential to enhance subsequent analysis and ensure the accuracy of results by reducing noise and unwanted artifacts. This paper provides an overview of state-of-the-art processing methods for HSI data, focusing on smoothing, normalization, and spectral derivatives. The efficacy of these methods is evaluated using root mean square error (RMSE) to compare pre-processed data with wavelength reference standard, alongside execution time considerations. Results indicate that certain algorithms, such as smoothing based on moving average, standard normal variate, and first spectral derivatives, yield superior performance across different medical HSI systems. Additionally, combining these processing techniques further improves data fidelity to the wavelength reference standard. Overall, this study offers insights into optimal processing strategies for enhancing the accuracy and reliability of HSI data.

Cardiovascular Diseases (CVDs) stand as the leading cause of mortality worldwide. Detecting subtle heart sounds alterations in the early stages of CVDs can be crucial for an initial effective treatment. Accordingly, the analysis of Phonocardiograms (PCGs) through segmentation could be helpful for CVDs screening. A well-established algorithm for this task is based on a Convolutional Neural Network (CNN) with an encoding-decoding topology. Prior to the CNN processing., a computationally intensive input pre-processing., based on envelopes extraction, is needed. Thus., achieving real-time performance can be challenging. The main goal of this study is the hardware design., implementation, and evaluation of four PCG pre-processing circuits to be employed together in the design of a low-power point-of-care device for real-time Artificial Intelligence (AI)-based PCG segmentation. Results have shown that the approximations introduced by the fixed-point format and this innovative architecture have a negligible impact on the AI segmentation quality. Finally, the pre-processing chain is real-time compliant., achieving a maximum latency of 257 ms for an available processing window of 1.28 s., while dissipating only 61 mW of power.

The purpose of this paper is to outline the advances in hyperspectral (HS) image fusion for intraoperative delineation of brain tumor tissue. HS images were acquired using an intraoperative acquisition system based on two push-broom HS cameras, one covering the visible and near-infrared (VNIR) [400–1000 nm] and the other the near-infrared (NIR) [900–1700 nm] spectral range. A dataset of a wide range of in-vivo brain cancer acquired during neurosurgical procedures with both HS cameras was used to compare the performance results of using the VNIR and NIR data, independently and combining the VNIR-NIR data. Classification maps obtained using the fused VNIR-NIR images provide more accurate classification, removing false positives that appear when the VNIR and NIR images are processed independently.

Chemotherapy-induced peripheral neuropathy (CIPN) is a common adverse reaction produced by chemotherapy drugs used to treat cancer. A few of the most common symptoms are pain, discomfort, tingling, numbness, and weakness in the hands, feet, and other parts of the body. The use of ozone therapy (O3T) is a novel therapy which aims to reduce these side effects. This study focuses on the visualization of oxygen saturation (StO2) in the extremities in a non-contact fashion employing hyperspectral (HS) imaging (HSI) with the goal of using HSI as a predictive value in the objective assessment of pain after ozone therapy application. A customized acquisition system composed of an HS camera (covering the 470–900 nm spectral range) and a halogen illumination system was developed to capture images of the extremities in a non-contact approach. An experimental clinical procedure was established to measure the evolution of StO2in hands and feet using a mathematical model based on information related to two wavelengths (660 and 880 nm). The preliminary results show that, in general, when analyzing the extremities of all unified patients, StO2slightly improves but significatively in the peripheral tissues after ozone therapy (O3T). HS technology allows the estimation of StO2values and allows the quantification of the effect of O3T.

Cardiovascular diseases (CVDs) are currently one of the leading causes of death worldwide. Being able to detect their symptoms at early stages, even the most hidden ones, is crucial to shorten the diagnosis time and facilitate an early treatment. Currently, the use of continuous tracking systems, mainly based on wearable devices that analyze data using artificial intelligence (AI) algorithms, is being explored to automatically identify, in real time, CVDs symptoms. This could be especially relevant in lowincome countries where there is a shortage of specialized doctors. Therefore, this work focuses on analyzing the real-time execution of the state-of-the-art convolutional neural network (CNN) for heart sound segmentation (HSS) on platforms such as traditional CPU/GPU and the Fraunhofer IMS © AIRISC Core Complex (a RISC-V processor developed for AI). Results revealed that, while all implementations exploiting the CPU/GPU platform proved to be useful in real-time diagnosis from a fixed location, the AIRISC demonstrated its goodness, as a system on a chip (SoC) for a real-time wearable application, when executing a quantized version of the CNN.

Noncommunicable Diseases (NCDs), like Cardiovascular Diseases (CVD) or Diabetes Mellitus (DM) are defined as chronic conditions caused by the combination of genetic, physiological, behavioral, and environmental factors that can affect an individual's health, being a major issue for the public health system globally. Sometimes, these conditions share some of their risk factors, as occurs between CVD and DM. Current clinically validated risk calculators have been developed using different regression approaches, targeting different populations and having significant differences between their outputs and the risk factors they use to compute the risk. In this work, we present a methodology for the design of risk calculator based on Machine Learning (ML), combining the knowledge of different clinically validated cardiovascular risk calculators using transfer learning for more personalized NCD risk estimation. Besides, a hardware profiling in terms of latency and model size is performed, targeting its real-time implementation in an embedded system. Results suggest that re-training an already developed ML model with a different dataset can improve its generalization capability, being a suitable way to avoid overfitting. Moreover, profiling results shown that this type of ML-based algorithms are suitable for embedded systems implementations., having model sizes lower than 1 KB and average inference times lower than$75\ \mu\mathrm{s}$.

Recently, several medical applications have relied on hyperspectral imaging. This technology enables both automated diagnosis and surgeon guidance. The employed algorithms adopt machine and deep learning methods to classify the images. In particular, Vision Transformers are a recent deep architecture that have been used to classify hyperspectral images of skin cancers achieving interesting results. However, deep architectures are computationally intensive and parallel architectures are mandatory to ensure a fast classification (depending on the application type even in real time). In this paper, we propose a parallel Vision Transformer architecture exploiting a low power GPU targeting the development of a portable diagnostic device. The classification time and power consumption of the low power board are compared with the performance of a desktop GPU. The results clearly highlight the suitability of the low power GPU to develop a portable diagnostic system based on hyperspectral imaging.

The increasing prevalence of chronic non-communicable diseases makes it a priority to develop tools for enhancing their management. On this matter, Artificial Intelligence algorithms have proven to be successful in early diagnosis, prediction and analysis in the medical field. Nonetheless, two main issues arise when dealing with medical data: lack of high-fidelity datasets and maintenance of patient's privacy. To face these problems, different techniques of synthetic data generation have emerged as a possible solution. In this work, a framework based on synthetic data generation algorithms was developed. Eight medical datasets containing tabular data were used to test this framework. Three different statistical metrics were used to analyze the preservation of synthetic data integrity and six different synthetic data generation sizes were tested. Besides, the generated synthetic datasets were used to train four different supervised Machine Learning classifiers alone, and also combined with the real data. F1-score was used to evaluate classification performance. The main goal of this work is to assess the feasibility of the use of synthetic data generation in medical data in two ways: preservation of data integrity and maintenance of classification performance.

It is my great pleasure to welcome you to the main EUROMICRO event, the joint 25th Digital Systems Design (DSD 2022) and the 48th Software Engineering and Advanced Applications (SEAA 2022) Conferences. The integration of these two high quality conferences enables connections and collaboration opportunities among these diverse but highly interrelated fields. I am honored to host the DSD/SEAA event in Gran Canaria, one of the most important islands of Canary Islands in Spain. Particularly, the event will be held in the south of the island, in Meloneras (Maspalomas), surrounded by a fascinating landscape of ravines and protected areas, and just seven hundred meters from the golden-sand beach of Maspalomas, declared Protected Natural Area with the category of Special Nature Reserve since 1994. The south of the island of Gran Canaria gathers most of the island's tourism and brings together a huge number of high-level hotels and holiday resorts. The COVID-19 pandemic has diminished the number of conferences held in-person over the past two years, moving many events to virtual and decreasing the face-to-face experience for researchers around the globe, logically prioritizing the health, safety, and wellbeing of the attendees. With the improved current situation, the DSD/SEAA Organizing Committee have decided to support the return to normality by planning a totally in-person event, but providing the possibility to authors of certain countries, which still cannot travel to Gran Canaria due to the COVID-19 restrictions, to give their presentations online. First of all, I would like to thank all the authors for their high-quality research and their decision to present their work at DSD/SEAA. I would also like to thank the Program Chairs, Himar Fabelo and Samuel Ortega for DSD, as well as Regina Hebig and Andreas Wortmann for SEAA, the Track Chairs, the Program Committees members, and associate reviewers for their excellent work to select high-quality works and provide meaningful feedback to authors. Additionally, I would like to take this opportunity to thank the entire DSD Steering Committee (Lech Jozwiak, Hana Kubatova, Paris Kitsos, Antonio Nuñez, Francesco Leporati, José Silva Matos, and Eugenio Villar), the entire SEAA Steering Committee (Michel Chaudron, Onur Demirors, Stefan Biffl and Rick Rabiser), the publication chair (Amund Skavhaung), the organizing chair (Pedro Carballo) and the publicity chair (João Canas Ferreira). Finally, I would like to thank the local organizing committee (Maria Castro, Raquel Leon, Abian Hernandez, Beatriz Martinez, Laura Quintana, Antonio Rodriguez, Carlos Vega and Eduardo Quevedo) for their continuous work and support in the preparation of the event. I hope DSD/SEAA in Gran Canaria will bring the relaxing atmosphere required for a profitable scientific experience and a wonderful personal stay.

Skin cancer is one of the most frequent type of cancer, which is tipically divided in two types: melanoma and non-melanoma. Melanoma is the least common, but also the deadliest of them if left untreated in early stages. Thus, skin cancer monitoring is key for early detection, which could be done with the help of mobile devices and artificial intelligence solutions. In this sense, local deployment is suggested to embrace simplicity and avoid data privacy and security issues. However, current high-performance neural networks are extremely challenging to be deployed in mobile devices due to resource constraint, so lighter but effective models are required to make local deployment possible. In this work, simplifying an already light model, such as MobileNetV2, is pursued, combining it with an attention mechanism to enhance the network's capability to learn and compensate for the lack of information that simplifying the original architecture might cause. Fine-tuning was applied, using an autoencoder to pre-train the model on the CIFAR100 dataset. Experiments covering four scenarios were carried out using HAM10000 dataset. Promising results were obtained, reaching the best performance using a simplified MobileNetV2 combined with Coordinate Attention mechanism with less than a million parameters in total and up to a 83.93 % of accuracy.

Today, hyperspectral (HS) imaging has become a powerful tool to identify remotely the composition of an interest area through the joint acquisition of spatial and spectral information. However, like in most imaging techniques, unwanted effects may occur during data acquisition, such as noise, changes in light intensity, temperature differences, or optical variations. In HS imaging, these problems can be attenuated using a reflectance calibration stage and optical filtering. Nevertheless, optical filtering might induce some distortion that could complicate the posterior image processing stage. In this work, we present a new proposal for reflectance calibration that compensates for optical alterations during the acquisition of an HS image. The proposed methodology was evaluated on an HS image of synthetic squares of various materials with specific spectral responses. The results of our proposal show high performance in two classification tests using the K-means algorithm with 97% and 88% accuracy; in comparison with the standard reflectance calibration from the literature that obtained 77% and 64% accuracy. These results illustrate the performance gain of the proposed formulation, which besides maintaining the characteristic features of the compounds within the HS image, keeps the resulting reflectance into fixed lower and upper bounds, which avoids a post-calibration normalization step.

Glioblastoma is considered an aggressive tumor due to its rapid growth rate and diffuse pattern in various parts of the brain. Current in-vivo classification procedures are executed under the supervision of an expert. However, this methodology could be subjective and time-consuming. In this work, we propose a classification method for in-vivo hyperspectral brain images to identify areas affected by glioblastomas based on nonlinear spectral unmixing. This methodology follows a semi-supervised approach for the estimation of the end-members in a multi-linear model. To improve the classification results, we vary the number of end-members per-class to address spectral variability of each studied type of tissue. Once the set of end-members is obtained, the classification map is generated according to the end-member with the highest abundance in each pixel, followed by morphological operations to smooth the resulting maps. The classification results demonstrate that the proposed methodology generates high performance in the regions of interest, with an accuracy above 0.75 and 0.96 in the inter and intra-patient strategies, respectively. These results indicate that the proposed methodology has the potential to be used as an assistant tool in the diagnosis of glioblastoma in hyperspectral imaging.

In recent years, hyperspectral imaging has been employed in several medical applications, targeting automatic diagnosis of different diseases. These images showed good performance in identifying different types of cancers. Among the methods used for classification, machine learning and deep learning techniques emerged as the most suitable algorithms to handle these data. In this paper, we propose a novel hyperspectral image classification architecture exploiting Vision Transformers. We validated the method on a real hyperspectral dataset containing 76 skin cancer images. Obtained results clearly highlight that the Vision Transforms are a suitable architecture for this task. Measured results outperform the state-of-the-art both in terms of false negative rates and of processing times. Finally, the attention mechanism is evaluated for the first time on medical hyperspectral images.

The early detection of precancerous cervical lesions is essential to improve patient treatment and prognosis. Current methods of screening and diagnosis have improved the detection of these lesions but still present some critical limitations. Hyperspectral (HS) imaging is emerging as a new non-invasive and label-free imaging technique in the medical field for performing quick diagnosis of different diseases. This work describes the first step in the research and development process to present to the gynaecologist a new non-invasive tool to detect cervical neoplasia during routine medical procedures. This tool is based on a HS camera coupled to a colposcope, a primary tool already used in cervical examinations. The developed HS colposcope was validated by comparing the HS images obtained against the captures obtained with conventional optics. Results show the feasibility of the developed system to start a data acquisition campaign of cervical lesions targeting future developments of algorithms based on artificial intelligence.

Oxygen saturation (StO2) measurement allows to detect different clinical conditions related with the low oxygenation of tissues or is used to monitor the quality and safety of organ transplantation. This study is focused on the visualization and measurement of StO2using hyperspectral imaging (HSI) through non-contact skin captures, targeting a potential real-time monitoring application. A customized acquisition system composed by a hyperspectral camera (covering the 470-900 nm spectral range) and a thermal camera was developed to capture images of hands in a non-contact fashion. An experimental procedure was established to measure the evolution of StO2in healthy hands where a compression of the index finger or brachial artery were performed. StO2measurements were performed in normal, compression, and reperfusion states. Two mathematical models with different sets of wavelengths were evaluated. The results show the proposed models, which employed two wavelengths (660 and 880 nm), obtain reliable StO2values, providing a potential non-contact imaging tool for StO2measurement.

This paper describes the challenge of real-time tumor tissue identification dealt with by the HypErspectraL Imaging Cancer Detection (HELICoiD) European project. This project was funded by the Research Executive Agency, through the Future and Emerging Technologies (FET-Open) programme, under the 7th Framework Programme of the European Union. It involved four universities, three industrial partners and two hospitals. In this paper, we focused on the activity performed by the University of Las Palmas de Gran Canaria, in collaboration with the University of Pavia, concerning the parallel implementation of Support Vector Machine (SVM) classification for tumor tissue identification during surgery. Obtained results show that this classification is real-time compliant when performed using Graphic Processing Units (GPUs).

This paper presents an efficient parallelization of the Motion Estimation procedure, one of the core parts of Super Resolution techniques. The algorithm considered is the basic version of Block Matching Super Resolution, with a single low-resolution camera and fixed Macro Block dimensions. Two are the implementations provided, with OpenMP and in CUDA on an NVIDIA Kepler GPU. Tests have been conducted on five image sequences and the results show a considerable improvement of the CUDA solution in all cases. Consequently, it can be stated that GPUs can efficiently accelerate computational times assuring the same image quality.

Recent advances in hyperspectral imaging have made it a promising solution for intra-operative tissue characterization, with the advantages of being non-contact, non-ionizing, and non-invasive. Working with hyperspectral images in vivo, however, is not straightforward as the high dimensionality of the data makes real-time processing challenging. In this paper, a novel dimensionality reduction scheme and a new processing pipeline are introduced to obtain a detailed tumor classification map for intra-operative margin definition during brain surgery. However, existing approaches to dimensionality reduction based on manifold embedding can be time consuming and may not guarantee a consistent result, thus hindering final tissue classification. The proposed framework aims to overcome these problems through a process divided into two steps: dimensionality reduction based on an extension of the T-distributed stochastic neighbor approach is first performed and then a semantic segmentation technique is applied to the embedded results by using a Semantic Texton Forest for tissue classification. Detailed in vivo validation of the proposed method has been performed to demonstrate the potential clinical value of the system.

Spectral unmixing is a popular technique for analyzing remotely sensed hyperspectral data sets with subpixel precision. Over the last few years, many algorithms have been developed for each of the main processing steps involved in spectral unmixing (SU) under the LMM assumption: 1) estimation of the number of endmembers; 2) identification of the spectral signatures of the endmembers; and 3) estimation of the abundance of endmembers in the scene. Although this general processing chain has proven to be effective for unmixing certain types of hyperspectral images, it also has some drawbacks. The first one comes from the fact that the output of each stage is the input of the following one, which favors the propagation of errors within the unmixing chain. A second problem is the huge variability of the results obtained when estimating the number of endmembers of a hyperspectral scene with different state-of-the-art algorithms, which influences the rest of the process. A third issue is the computational complexity of the whole process. To address the aforementioned issues, this paper develops a novel negative abundance-oriented SU algorithm that covers, for the first time in the literature, the main steps involved in traditional hyperspectral unmixing chains. The proposed algorithm can also be easily adapted to a scenario in which the number of endmembers is known in advance and two additional variations of the algorithm are provided to deal with high-noise scenarios and to significantly reduce its execution time, respectively. Our experimental results, conducted using both synthetic and real hyperspectral scenes, indicate that the presented method is highly competitive (in terms of both unmixing accuracy and computational performance) with regard to other SU techniques with similar requirements, while providing a fully self-contained unmixing chain without the need for any input parameters.

Hyperspectral image processing represents a valuable tool for remote sensing of the Earth. This fact has led to the inclusion of hyperspectral sensors in different airborne and satellite missions for Earth observation. However, one of the main drawbacks encountered when dealing with hyperspectral images is the huge amount of data to be processed, in particular, when advanced analysis techniques such as spectral unmixing are used. The main contribution of this letter is the introduction of a novel preprocessing (PP) module, called SE2PP, which is based on the integration of spatial and spectral information. The proposed approach can be combined with existing algorithms for endmember extraction, reducing the computational complexity of those algorithms while providing similar figures of accuracy. The key idea behind SE2PP is to identify and select a reduced set of pixels in the hyperspectral image, so that there is no need to process a large amount of them to get accurate spectral unmixing results. Compared to previous approaches based on similar spatial and spatial-spectral PP strategies, SE2PP clearly outperforms their results in terms of accuracy and computation speed, as it is demonstrated with artificial and real hyperspectral images.

Endmember extraction represents one of the most challenging aspects of hyperspectral image processing. In this letter, a new algorithm for endmember extraction, named modified vertex component analysis (MVCA), is presented. This new technique outperforms the popular vertex component analysis (VCA) by applying a low-complexity orthogonalization method and by utilizing integer instead of floating-point arithmetic when dealing with hyperspectral data. The feasibility of this technique is demonstrated by comparing its performance with VCA on synthetic mixtures as well as on the well-known Cuprite hyperspectral image. MVCA shows promising results in terms of much lower computational complexity, still reproducing similar endmember accuracy than its original counterpart. Moreover, the features of this algorithm combined with state-of-the-art hardware implementations qualify MVCA as a good potential candidate for all those applications in which real time is a must.

Systems relying on fixed hardware components with a static level of parallelism can suffer from an under use of logical resources, since they have to be designed for the worst-case scenario. This problem is especially important in video applications due to the emergence of new flexible standards, like Scalable Video Coding (SVC), which offer several levels of scalability. In this paper, Dynamic and Partial Reconfiguration (DPR) of modern FPGAs is used to achieve run-time variable parallelism, by using scalable architectures where the size can be adapted at run-time. Based on this proposal, a scalable Deblocking Filter core (DF), compliant with the H.264/AVC and SVC standards has been designed. This scalable DF allows run-time addition or removal of computational units working in parallel. Scalability is offered together with a scalable parallelization strategy at the macro block (MB) level, such that when the size of the architecture changes, MB filtering order is modified accordingly.

A highly parallel and scalable Deblocking Filter (DF) hardware architecture for H.264/AVC and SVC video codecs is presented in this paper. The proposed architecture mainly consists on a coarse grain systolic array obtained by replicating a unique and homogeneous Functional Unit (FU), in which a whole Deblocking-Filter unit is implemented. The proposal is also based on a novel macroblock-level parallelization strategy of the filtering algorithm which improves the final performance by exploiting specific data dependences. This way communication overhead is reduced and a more intensive parallelism in comparison with the existing state-of-the-art solutions is obtained. Furthermore, the architecture is completely flexible, since the level of parallelism can be changed, according to the application requirements. The design has been implemented in a Virtex-5 FPGA, and it allows filtering 4CIF (704 × 576 pixels @30 fps) video sequences in real-time at frequencies lower than 10.16 Mhz.

In this work we present a novel execution flow for the super-resolution image restoration (SRIR) non-uniform grid projection algorithm - the macroblock-level flow. The novel flow is compared with the reference frame-level flow. The frame-level flow is characterized by the fact that transitions from one step of the algorithm to another occur only after the current step is carried out for all macro blocks (MBs) of the frame being currently processed. The novel flow carries out complete processing of one MB before the processing of another MB starts. The memory requirements of both schemes are evaluated in detail and compared. The study on the achievable memory reduction in total memory requirements was carried out for different values of the algorithm parameters: the MB size, scale factor, search area size and number of reference frames included in the sliding frame window. The results show quantitatively that the parameter that influences storage instantiation the most and has the greatest influence on the total memory size is the number of reference frames in the sliding frame window. The conducted study shows that, for a QCIF frame format, switching from frame-to macroblock-level is feasible and fully validated functionally and that the new execution flow can lead to memory reduction by a factor of 6.8 to 40, depending on the algorithm parameters values. Memory reduction greatly facilitates hardware implementations of the algorithm and this is the main result claimed. But the reduction in memory size comes at the cost of increasing the number of memory accesses and therefore communications traffic. The increase noted in memory accesses it to be quantified in future work as well as the potential impact on power consumption. The reduction in memory size might also make it fit on chip without turning to external memory, thereby reducing power consumption. This trade off in power is yet to be quantified.

Nowadays, images are employed in several areas of medicine for early diagnosis. In this sense, the industry provides accurate models to obtain, for example, X-ray and cardiology images of high resolution. However, other images, such as those related to pathological anatomy present in many situations poor quality, which complicates the diagnostic process. This work is focused on the quality enhancement of this type of images through a system based on super-resolution techniques. The results show that the proposed methodology can help medical specialists in the diagnostic of several pathologies.

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 slightly 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.

As SoC complexity grows new methodologies and tools for system design and time-effective ditsign space exploration are required. In this paper we introduce a tool called CASSE, what stands for Camellia system-on-chip simulation environment. CASSE is a fast, flexible, and modular SystemC-based simulation environment which aims to be useful for design-space exploration and system-level design at different abstraction levels. The tool uses transaction-level modeling techniques for fast simulations and easy architectural modeling, and bridge the gap to system implementation by a progressive refinement approach. CASSE is being used in the European 1ST-2001-34410 CAMELLIA project, which focuses on the mapping of innovative smart imaging applications onto an existing video encoding architecture.