- Video Surveillance and Tracking Methods
- Face recognition and analysis
- Remote-Sensing Image Classification
- Face and Expression Recognition
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Biometric Identification and Security
- Infrared Thermography in Medicine
- Kidney Stones and Urolithiasis Treatments
- Laser-induced spectroscopy and plasma
- Remote Sensing and Land Use
- Soil Moisture and Remote Sensing
- Advanced Image Fusion Techniques
- Advanced SAR Imaging Techniques
- Intraocular Surgery and Lenses
- Quantum Information and Cryptography
- Anomaly Detection Techniques and Applications
- Traumatic Ocular and Foreign Body Injuries
- Quantum Mechanics and Applications
- Advanced Vision and Imaging
- Handwritten Text Recognition Techniques
- Remote Sensing and LiDAR Applications
- Medical Image Segmentation Techniques
- Quantum Computing Algorithms and Architecture
- Gait Recognition and Analysis
- Remote Sensing in Agriculture
University of Patras
2016-2025
University of Thessaly
2018
This research paper presents a robust image registration algorithm tailored for the accurate estimation of displacements. Image is fundamental task in computer vision and processing, with applications ranging from medical imaging to motion tracking surveillance systems. The algorithm’s efficacy explored through series experiments conducted on pairs, both scenarios without noise those affected by additive noise. core methodology involves combination techniques, including Fourier transforms,...
Accurate and robust information on land cover changes in urban coastal areas is essential for effective management, ecosystem monitoring, planning. This paper details the methodology results of a pixel-level classification change detection analysis, leveraging 1945 Royal Air Force (RAF) aerial imagery 2011 Very High-Resolution (VHR) multispectral WorldView-2 satellite from broader area Patras, Greece. Our attention mainly focused coastline city Patras to northeast direction two major rivers,...
In the ever-evolving landscape of tomographic imaging algorithms, this literature review explores a diverse array themes shaping field’s progress. It encompasses foundational principles, special innovative approaches, implementation and applications tomography in medicine, natural sciences, remote sensing, seismology. This choice is to show off diversity simultaneously new trends recent years. Accordingly, evaluation backprojection methods for breast reconstruction highlighted. After that,...
Virtual BasketTM , Bubble BlastTM and Vapor TunnelTM are three laser pulse modulation technologies that modify the holmium: yttrium-aluminum-garnet (Ho:YAG) transmission through creation of bubbles emerging from fiber tip with different effects on target stone. The primary outcome current study was to test stone ablation rates for modes, Basket, Blast, Tunnel, using power, energy, frequency settings.Quanta Cyber: Ho 150 WTM a 365 µm PrecisionTM fiber, hard soft phantom BegoStonesTM were used...
Drunk person identification is carried out using thermal infrared images. Two different approaches are proposed for distinguishing a drunk by means of radiometric values on its face. The features used in the first approach simply pixel specific points face person. It proved that cluster moves feature space as consumes alcohol. Fisher linear discriminant dimensionality reduction. found to be very low dimensionality. majority clusters towards same direction and can easily separated into...
To compare the retropulsion of stones with use holmium: yttrium aluminum garnet (Ho: YAG) laser and thulium: (Tm: in settings that could be used clinical practice.The experimental configuration included a glass tube set water bath filled physiologic saline. Plaster Paris were inserted tube. Tm: YAG Ho: systems along high-speed slow-motion camera. The lasers activated different settings. displacement stone was measured according to custom-made algorithm.Ho: YAG: lowest energy setting 0.5 J...
Higher-order statistics investigate the phase relationships between frequency components, an aspect which cannot be treated using conventional spectral measures such as power spectrum. Among widely used higher-order statistics, bispectrum ranks prominently. By delving into correlations, offers a means of extracting additional merits and insights from coupling, enhancing our understanding complex signal interactions. This analytical approach overcomes limitations traditional methods,...
Decision fusion plays a crucial role in achieving cohesive and unified outcome by merging diverse perspectives. Within the realm of remote sensing classification, these methodologies become indispensable when synthesizing data from multiple sensors to arrive at conclusive decisions. In our study, we leverage fully Polarimetric Synthetic Aperture Radar (PolSAR) thermal infrared establish distinct decisions for each pixel pertaining its land cover classification. To enhance classification...
Abstract Temperature distribution on the eyes of drunk persons is studied by means thermal infrared images. The sclera and iris are same temperature for sober person, while intoxicated increases. Consequently, only images from necessary intoxication screening. Forty‐one participants drank in a controlled alcohol consumption procedure. Their breath concentration was above threshold 0.2 mg/L exhaled air, which corresponds to about 0.5 mg per cubic centimeter blood. Histogram modification...
In this work, the activity of facial blood vessels drunk persons is studied using thermal infrared images. Nonlinear anisotropic diffusion applied to enhance on images and after that top-hat transformation used for isolating them from rest information face. Simple thresholding raise more active vessels. Registration procedures are employed easily compare vessel face person with sober person. persons, around nose eyes as well forehead become active. This work constitutes a preliminary study,...
Remote Sensing plays a fundamental role in acquiring crucial information about the Earth’s surface from distance, especially through fully polarimetric data, which offers rich source of for diverse applications. However, extracting meaningful insights this intricate data necessitates sophisticated techniques. In addressing challenge, one predominant trend that has emerged is known as target decomposition These techniques can be broadly classified into coherent and non-coherent methods. Each...
Sunspot daily time series have been available for almost two centuries providing vast and complicated information about the behavior of our star especially interaction motion planets other possible interstellar phenomena their effects on surface Sun. The main result obtained from sunspot analysis is imprint various periodicities, such as planets’ orbital periods planetary synodic sunspots signature. A detailed spectrum representation achieved by means a periodogram virtual extension length...
Urban planning has, in recent years, been significantly assisted by remote sensing data. The data and techniques that are used very diverse available to government agencies as well private companies involved urban peri-urban areas. Synthetic aperture radar particularly important since they provide information on the geometric electrical characteristics of ground objects and, at same time, unaffected sunlight (day–night) cloud cover. SAR usually combined with optical (fusion) order increase...
The analysis of ground-penetrating radar (GPR) data is vital importance for detecting various subsurface features that might manifest as hyperbolic peaks, which are indicators a buried object or grayscale variation in the case contrast soil texture. This method focuses on identifying exaggerated patterns through series image-processing steps. Two GPR images initially read and preprocessed by extracting channels, flipping, resizing. Then, specific regions interest (ROIs) cropped, Fourier...
For Unmanned Aerial Vehicles (UAVs), it is of crucial importance to develop a technically advanced Collision Avoidance System (CAS). Such system must necessarily consist many sensors various types, each one having special characteristics and performance. The poor performance the can lead total failure in collision avoidance if there no provision for separate sensor be continuously monitored. In this work, Sensor Autonomous Integrity Monitoring (SAIM) methodology proposed. configuration their...
A novel land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) employed to characterize pixel by pixel. Cameron's CTD since it provides a complete set elementary scattering mechanisms describe physical properties scatterer. novelty proposed approach lies on fact that features used for are not types scatterers themselves, but way these alternate from image. Thus, transition matrices...
Drunk person identification is investigated in this work by means of applying neural networks on infrared images faces. The were acquired during controlled alcohol consumption twenty persons. Since the sample persons employed experimental procedure was small, proposed approach gives only indications which locations face are prominent to present significant changes with consumption. Applying each a different location we investigate their capability converge specific locations. It found that...
This study exploits Cameron’s decomposition for polarimetric data analysis and presents an information extraction process so that each PolSAR cell (pixel) is interpreted by two dominating elementary scattering mechanisms one contributing to the behavior of SAR pixel with its own weight. The co-distance matrix introduced depict metric distances between these nearest mechanisms. For most in resolution cell, strength first second scatterer usually differs slightly. indicates interpretation...
The high-power holmium: yttrium-aluminum-garnet lasers provide a wide variety of settings for stone disintegration. aim this in vitro study is to evaluate the effect short and long pulse duration on ablation rates urinary stones.Two types artificial stones were created by BegoStone™ with different compositions (15:3 15:6, stone/water ratio). Stones 15:3 15:6 powder-to-water ratio defined as hard soft stones, respectively. Lithotripsy was performed laser using custom-made model consisting 60...
Drunk person identification is carried out using thermal infrared images. The features used for this purpose are simply the pixel values on specific points face of person. It proved that a drunk person, corresponding cluster in feature space moves far away from its original position sober concept behind proposed approach based physiology-based identification. For demonstration purposes, Fisher Linear Discriminant dimensionality reduction. found to be very low dimensionality.