Tools for Transform Coding in coding of video relied on DCT-II traditionally for mapping residuals of image/video signals. Residual mapping can be done to a domain where quantizing and encoding tools give better effic...
详细信息
A literature review is an essential part of research. Beginning researchers who would like to conduct research in any field commonly review previous papers to identify trends and gaps in research. However, conducting ...
详细信息
Studying circumstellar environments is crucial for understanding exoplanets and stellar systems. Instruments like SPHERE can extract information about these environments by leveraging advanced image reconstruction met...
详细信息
ISBN:
(数字)9789464593617
ISBN:
(纸本)9798331519773
Studying circumstellar environments is crucial for understanding exoplanets and stellar systems. Instruments like SPHERE can extract information about these environments by leveraging advanced image reconstruction methods, possibly based on deep learning. This work focuses on unfolded proximal neural networks based on Condat- vii iterations and proposes a new nonlinear formulation. To evaluate and compare the performance of the proposed reconstruction strategies, two datasets dedicated to circumstellar environments analysis in the context of high-contrast imagery have been created offering different level of complexity in the evaluation of the performance.
Real-time video surveillance systems are widely deployed in various environments, including public areas, commercial buildings, and public infrastructures. Person detection is a key and crucial task in different video...
详细信息
This predoctoral research project is carried out in the framework of an international co-tutelage between the University of Jaén and the Universidad Autónoma de Occidente in Cali, Colombia with the participa...
详细信息
ISBN:
(数字)9798350364538
ISBN:
(纸本)9798350364545
This predoctoral research project is carried out in the framework of an international co-tutelage between the University of Jaén and the Universidad Autónoma de Occidente in Cali, Colombia with the participation of the CyTI Department of the Universidad de San Buenaventura. Its main objective is to systematize the processes of maintenance and diagnosis of modules in Photovoltaic systems (PVS) using computational tools based on Artificial Intelligence (AI). The project seeks to reduce operating costs, minimize human errors and detect possible failures early, in order to extend the operating hours of the PV systems and reduce the time spent on preventive maintenance. To achieve these objectives, deep learning algorithms are used in infrared (IR) imageprocessing. These algorithms make it possible to evaluate the state of the photovoltaic modules by analyzing variations in surface temperatures, detecting anomalous situations and failures in each photovoltaic (PV) collector module. The implementation of these techniques will contribute to the development of effective methodologies that will significantly improve PV maintenance. This advance represents significant progress in the efficiency and sustainability of solar photovoltaic energy, with applications of great relevance in both the scientific and technological *** proyecto de investigación predoctoral se lleva a cabo en el marco de una cotutela internacional entre la Universidad de Jaén y la Universidad Autónoma de Occidente en Cali, Colombia con la participación del Departamento de CyTI de la Universidad de San Buenaventura. Su objetivo principal es sistematizar los procesos de mantenimiento y diagnóstico de módulos en Sistemas Fotovoltaicos (SFV) mediante el uso de herramientas computacionales basadas en Inteligencia Artificial (IA). El proyecto busca reducir costos operativos, minimizar errores humanos y detectar tempranamente posibles fallos, con el fin de prolongar las horas de funcionamiento de los SFV
A multi-cascade adaptive optical system for imaging and image stabilization for the Large Solar Vacuum Telescope is described. This system was created in 2017 by specialists of the V.E. Zuev Institute of Atmospheric O...
详细信息
ISBN:
(纸本)9781510636842
A multi-cascade adaptive optical system for imaging and image stabilization for the Large Solar Vacuum Telescope is described. This system was created in 2017 by specialists of the V.E. Zuev Institute of Atmospheric Optics SB RAS, Tomsk, with the technical support of the Institute of Solar-Terrestrial Physics SB RAS, Irkutsk. The system has been tested at the Large Solar Vacuum Telescope (Baikal Astrophysical Observatory) and demonstrated its efficiency. Along with the first cascade of adaptive image stabilization by a tip-tilt corrected mirror, this system employs the second imaging cascade based on correction with a flexible mirror controlled by a specialized wavefront sensor, as well as the third cascade for real-time post-detector processing of video camera frames. Reliable experimental data confirming the efficiency of the multi-cascade adaptive system for image formation and stabilization have been obtained. Three high-rate digital video cameras recording simultaneously digital images with rates from 300 to 980 frames per second were used to test the system. The mirror correcting wavefront tilts and operating in a closed optical feedback loop was controlled by the specially developed software including the fast correlation tracking algorithm. The post-detector digital imaging was performed with a special software for processing of video camera frames in real time with the use of modern high-speed parallel algorithms based on the Intel MKL and IPP libraries.
The Exoplanet Imaging Data Challenge is a community-wide effort meant to offer a platform for a fair and common comparison of imageprocessing methods designed for exoplanet direct detection. For this purpose, it gath...
详细信息
ISBN:
(纸本)9781510636842
The Exoplanet Imaging Data Challenge is a community-wide effort meant to offer a platform for a fair and common comparison of imageprocessing methods designed for exoplanet direct detection. For this purpose, it gathers on a dedicated repository (Zenodo), data from several high-contrast ground-based instruments worldwide in which we injected synthetic planetary signals. The data challenge is hosted on the CodaLab competition platform, where participants can upload their results. The specifications of the data challenge are published on our website https://***/. The first phase, launched on the 1st of September 2019 and closed on the 1st of October 2020, consisted in detecting point sources in two types of common data-set in the field of high-contrast imaging: data taken in pupil-tracking mode at one wavelength subchallenge 1, also referred to as ADI) and multispectral data taken in pupil-tracking mode (subchallenge 2, also referred to as ADI+mSDI). In this paper, we describe the approach, organisational lessons-learnt and current limitations of the data challenge, as well as preliminary results of the participants' submissions for this first phase. In the future, we plan to provide permanent access to the standard library of data sets and metrics, in order to guide the validation and support the publications of innovative imageprocessingalgorithms dedicated to high-contrast imaging of planetary systems.
Despite the benefits introduced by robotic systems in abdominal Minimally Invasive Surgery (MIS), major complications can still affect the outcome of the procedure, such as intra-operative bleeding. One of the causes ...
详细信息
Despite the benefits introduced by robotic systems in abdominal Minimally Invasive Surgery (MIS), major complications can still affect the outcome of the procedure, such as intra-operative bleeding. One of the causes is attributed to accidental damages to arteries or veins by the surgical tools, and some of the possible risk factors are related to the lack of sub-surface visibilty. Assistive tools guiding the surgical gestures to prevent these kind of injuries would represent a relevant step towards safer clinical procedures. However, it is still challenging to develop computer vision systems able to fulfill the main requirements: (i) long term robustness, (ii) adaptation to environment/object variation and (iii) real time processing. The purpose of this paper is to develop computer vision algorithms to robustly track soft tissue areas (Safety Area, SA), defined intra-operatively by the surgeon based on the real-time endoscopic images, or registered from a pre-operative surgical plan. We propose a framework to combine an optical flow algorithm with a tracking-by-detection approach in order to be robust against failures caused by: (i) partial occlusion, (ii) total occlusion, (iii) SA out of the field of view, (iv) deformation, (v) illumination changes, (vi) abrupt camera motion, (vii), blur and (viii) smoke. A Bayesian inference-based approach is used to detect the failure of the tracker, based on online context information. A Model Update Strategy (MUpS) is also proposed to improve the SA re-detection after failures, taking into account the changes of appearance of the SA model due to contact with instruments or image noise. The performance of the algorithm was assessed on two datasets, representing ex-vivo organs and in-vivo surgical scenarios. Results show that the proposed framework, enhanced with MUpS, is capable of maintain high tracking performance for extended periods of time (similar or equal to 4 min - containing the aforementioned events) with high precisi
A new generation of the WILLIAM (WIde-field aLL-sky image Analyzing Monitoring system) camera includes new features such as monitoring of rain and storm clouds during the day observation. Development of the new genera...
详细信息
ISBN:
(数字)9781510617032
ISBN:
(纸本)9781510617032;9781510617025
A new generation of the WILLIAM (WIde-field aLL-sky image Analyzing Monitoring system) camera includes new features such as monitoring of rain and storm clouds during the day observation. Development of the new generation of weather monitoring cameras responds to the demand for monitoring of sudden weather changes. However, new WILLIAM cameras are ready to process acquired image data immediately, release warning against sudden torrential rains, and send it to user's cell phone and email. Actual weather conditions are determined from image data, and results of imageprocessing are complemented by data from sensors of temperature, humidity, and atmospheric pressure. In this paper, we present the architecture, image data processingalgorithms of mentioned monitoring camera and spatially-variant model of imaging system aberrations based on Zernike polynomials.
Multiplier-free fast algorithms are derived and analyzed for realizing the 8-point discrete sine transform of type II and type vii (DST-II and DST-vii) transforms with applications in image and video compression. A ne...
详细信息
Multiplier-free fast algorithms are derived and analyzed for realizing the 8-point discrete sine transform of type II and type vii (DST-II and DST-vii) transforms with applications in image and video compression. A new fast algorithm is identified using numerical search methods for approximating DST-vii without employing multipliers. In addition, recently proposed fast algorithms for approximating the 8-point DCT-II are now extended to approximate DST-II. All proposed approximations for DST-II and DST-vii are compared with ideal transforms, and circuit complexity is measured using FPGA-based rapid prototypes on a 90nm Xilinx Virtex-4 device. The proposed architectures find applications in emerging video processing standards such as H.265/HEVC.
暂无评论