Search results for: IMAGES ANALYSIS
-
Histogram of Gradients with Cell Average Intensity for Human Detection
PublicationThe modification of the descriptor in human detector using Histogram of Oriented Gradients and support vector machine is presented. The proposed modification requires inserting the average cell intensitiesresulting with the increase of the length of the descriptor from 3780 to 4200 values, but it is easy to compute and instantly gives 14-26% of miss rate improvement at 10^-4 False Positives Per Window (FPPW). The modification...
-
Changing by light - how the lighting of intelligent spaces can influence the urban image
PublicationIn the article light will be presented as a tool in the process of transforming the urban space. The reason for this use of light is the commercial aspect of space that forces it to be still competitive and profitable. Such a need gives rise to many innovative solutions in the city space, which allow transmitting information in order to attract human attention, and sometimes make it even possible to involve the user in the interaction...
-
Experiment with small objects floating under water in the harbor security aspect.
PublicationObservation of the underwater area is the element of general trend which primary purpose is to protect and enhance the safety of the selected region. The aim of the paper is to present the acoustic characteristics of typical objects floating on the surface or under the water, which constitute some knowledge on how to detect these objects. Create a catalog of acoustic signatures and acoustic images of objects mostly floating under...
-
An Improved Convolutional Neural Network for Steganalysis in the Scenario of Reuse of the Stego-Key
PublicationThe topic of this paper is the use of deep learning techniques, more specifically convolutional neural networks, for steganalysis of digital images. The steganalysis scenario of the repeated use of the stego-key is considered. Firstly, a study of the influence of the depth and width of the convolution layers on the effectiveness of classification was conducted. Next, a study on the influence of depth and width of fully connected...
-
CNN Architectures for Human Pose Estimation from a Very Low Resolution Depth Image
PublicationThe paper is dedicated to proposing and evaluating a number of convolutional neural network architectures for calculating a multiple regression on 3D coordinates of human body joints tracked in a single low resolution depth image. The main challenge was to obtain a high precision in case of a noisy and coarse scan of the body, as observed by a depth sensor from a large distance. The regression network was expected to reason about...
-
Interpolation methods in GPR tomographic imaging of linear and volume anomalies for cultural heritage diagnostics
PublicationThis paper presents results of a ground penetrating radar (GPR) survey conducted in St. Joseph’s Church in Gdańsk, Poland. The aim of the study was to produce tomographic imaging of a renovated floor as well as the objects buried under the floor to detect linear and volume inclusions. The assumed track spacing was meaningfully greater than the single signal spacing in each track, which induced the need for interpolation methods...
-
Single-Slope ADC With Embedded Convolution Filter for Global-Shutter CMOS Image Sensors
PublicationThis brief presents an analog-to-digital converter (ADC) suitable for acquisition and processing of images in the global-shutter mode at the pixel level. The ADC consists of an analog comparator, a multi-directional shift register for the comparator states, and a 16-bit reversible binary counter with programmable step size. It works in the traditional single-slope mode. The novelty is that during each step of the reference ramp,...
-
Deep Learning-Based, Multiclass Approach to Cancer Classification on Liquid Biopsy Data
PublicationThe field of cancer diagnostics has been revolutionized by liquid biopsies, which offer a bridge between laboratory research and clinical settings. These tests are less invasive than traditional biopsies and more convenient than routine imaging methods. Liquid biopsies allow studying of tumor-derived markers in bodily fluids, enabling the development of more precise cancer diagnostic tests for screening, disease monitoring, and...
-
Evolution of electrohydrodynamic flow of sduspended particles in a needle-to-plate negative DC corona discharge in air
PublicationCorona discharges are used for collecting dust in electrostatic precipitators (ESPs). The dust collection is mainlyrealized by the electric forces which move the ionized dust particles to the collecting electrodes. However, the presence of coronadischarge in the space between the charging and collecting electrodes in ESPs causes also the so-called ionic wind which set the gasmolecules and dust...
-
Multimodal Surveillance Based Personal Protection System
PublicationA novel, multimodal approach for automatic detection of abduction of a protected individual, employing dedicated personal protection device and a city monitoring system is proposed and overviewed. The solution is based on combining four modalities (signals coming from: Bluetooth, fixed and PTZ cameras, thermal camera, acoustic sensors). The Bluetooth signal is used continuously to monitor the protected person presence, and in case...
-
Static and dynamic concrete calculations: Breakable aggregates in DEM model
PublicationThe paper deals with the calculations of a 3-point bending beam under static and dynamic loads. The real microstructure was obtained from laboratory tests using micro-tomography images. The quasi-static results were compared directly with experimental data at both macro and micro levels. Subsequently, higher strain rates were applied to investigate dynamic effects. The study focused on the influence of dynamic loading on the macroscopic...
-
Evaluation of the Cathodic Electrodeposition Effectiveness of the Hydroxyapatite Layer Used in Surface Modification of Ti6Al4V-Based Biomaterials
PublicationThe important issue associated with the design and the fabrication of the titanium and titanium alloy implants is the increase of their biointegration with bone tissue. In the presented paper, the research results concerning the conditions used in the cathodic deposition of hydroxyapatite on the surface Ti6Al4V substrates primarily modified by the production of TiO2 nanoporous coatings, TiO2 nanofibers, and titanate coatings, are...
-
Electrocatalytic oxidation of methanol, ethylene glycol and glycerine in alkaline media on TiO2 nanotubes decorated with AuCu nanoparticles for an application in fuel cells
PublicationIn this work, we present the catalytic and photocatalytic activity of AuCu nanostructures obtained on TiO2 nanotubes toward methanol, ethylene glycol and glycerine oxidation. The electrode material is prepared by anodization of Ti foil, thin AuCu layer sputtering and rapid thermal treatment under argon atmosphere. Scanning electron microscopy images confirmed the presence of ordered tubular architecture of TiO2 as well as nanoparticles...
-
Fluid–Structure Interaction methods for the progressive anatomical and artificial aortic valve stenosis
PublicationCardiovascular system diseases, as aortic valve stenosis, are the main cause of mortality and morbidity among patients. There is still a room for enhancement of the diagnostic and therapeutic procedures, which will lead to improvement of the treatment. One of the remedies are the computer tools to support the medical diagnoses and prostheses design. The development of a procedure for modeling the aortic valves: anatomical tricuspid...
-
Multiclass AdaBoost Classifier Parameter Adaptation for Pattern Recognition
PublicationThe article presents the problem of parameter value selection of the multiclass ``one against all'' approach of an AdaBoost algorithm in tasks of object recognition based on two-dimensional graphical images. AdaBoost classifier with Haar features is still used in mobile devices due to the processing speed in contrast to other methods like deep learning or SVM but its main drawback is the need to assembly the results of binary...
-
THE ROLE OF INFERENCE IN MOBILE MEDICAL APPLICATION DESIGN
PublicationIn the early 21st century, artificial intelligence began to be used to process medical information. However, before this happened, predictive models used in healthcare could only consider a limited number of variables, and only in properly structured and organised medical data. Today, advanced tools based on machine learning techniques - which, using artificial neural networks, can explore extremely complex relationships - and...
-
Recovering Evaluation of Narrow-Kerf Teeth of Mini Sash Gang Saws
PublicationSash gang saws with narrow-kerf saw blades are used in the production of glued laminate flooring elements in plants where dry technology is applied. This means that boards or friezes are sawn into top layer lamellae in dry conditions (moisture content of about 10–12%) from expensive wood species, often exotic. The object of this research was stellite-tipped teeth of narrow kerf saw blades sharpened under industrial conditions....
-
Improving Traffic Light Recognition Methods using Shifting Time-Windows
PublicationWe propose a novel method of improving algorithms recognizing traffic lights in video sequences. Our focus is on algorithms for applications which notify the driver of a light in sight. Many existing methods process images in the recording separately. Our method bases on the observation that real-life videos depict underlying continuous processes. We named our method FSA (Frame Sequence Analyzed). It is applicable for any underlying...
-
Improving methods for detecting people in video recordings using shifting time-windows
PublicationWe propose a novel method for improving algorithms which detect the presence of people in video sequences. Our focus is on algorithms for applications which require reporting and analyzing all scenes with detected people in long recordings. Therefore one of the target qualities of the classification result is its stability, understood as a low number of invalid scene boundaries. Many existing methods process images in the recording...
-
Gas Composition Influence on the Properties of Boron-Doped Diamond Films Deposited on the Fused Silica
PublicationThe main subject of this study are molecular structures and optical properties of boron-doped diamond films with [B]/[C] ppm ratio between 1000 and 10 000, fabricated in two molar ratios of CH 4 -H 2 mixture (1 % and 4 %). Boron-doped diamond (BDD) film on the fused silica was presented as a conductive coating for optical and electronic purposes. The scanning electron microscopy images showed homogenous and polycrystalline surface...
-
Open smart glasses development platform for AAL applications
PublicationThis paper describes an open platform for multi sensory electronic glasses that supports new and enhanced methods for intelligent interaction with patients, with smart objects, or to be used as new data input modalities like proximity sensor or smart textile interfaces. All the activities have been developed, investigated and evaluated within EU CHIST-ERA eGlasses project...
-
On Algorithm Details in Multibeam Seafloor Classification
PublicationRemote sensing of the seafloor constitutes an important topic in exploration, management, protection and other investigations of the marine environment. In the paper, a combined approach to seafloor characterisation is presented. It relies on calculation of several descriptors related to seabed type using three different types of multibeam sonar data obtained during seafloor sensing, viz.: 1) the grey-level sonar images (echograms)...
-
Deep Features Class Activation Map for Thermal Face Detection and Tracking
PublicationRecently, capabilities of many computer vision tasks have significantly improved due to advances in Convolutional Neural Networks. In our research, we demonstrate that it can be also used for face detection from low resolution thermal images, acquired with a portable camera. The physical size of the camera used in our research allows for embedding it in a wearable device or indoor remote monitoring solution for elderly and disabled...
-
Sea bottom structure investigation by means of acoustic methods
PublicationThe main aim of the paper is the result of experimental investigations of the seabed in the Gulf of Gdańsk arried out using parametric echosounder as a main measuring tool. Examination of the surface's upper layer of the seabed, especially is acoustic properties, reflecting most often transsmision and reflection properties of the incident elastic wave, could be a valuable material for determination of the stratification, and the...
-
FPGA-Based Implementation of Real Time Optical Flow Algorithm and Its Applications for Digital Image Stabilization
PublicationAn efficient simplification procedure of the optical flow (OF) algorithm as well as its hardware implementation using the field programmable gate array (FPGA) technology is presented. The modified algorithm is based on block matching of subsets of successive frames, and exploits one-dimensional representation of subsets as well as the adaptive adjustments of their sizes. Also, an l1-norm-based correlation function requiring no...
-
ColorNephroNet: Kidney tumor malignancy prediction using medical image colorization
PublicationRenal tumor malignancy classification is one of the crucial tasks in urology, being a primary factor included in the decision of whether to perform kidney removal surgery (nephrectomy) or not. Currently, tumor malignancy prediction is determined by the radiological diagnosis based on computed tomography (CT) images. However, it is estimated that up to 16% of nephrectomies could have been avoided because the tumor that had been...
-
Multidecadal (1960-2011) shoreline changes in Isbjornhamna (Hornsund, Svalbard)
PublicationAsection of a gravel−dominated coast in Isbjørnhamna (Hornsund, Svalbard) was analysed to calculate the rate of shoreline changes and explain processes controlling coastal zone development over last 50 years. Between 1960 and 2011, coastal landscape of Isbjørn− hamna experienced a significant shift from dominated by influence of tide−water glacier and protected by prolonged sea−ice conditions towards storm−affected and rapidly...
-
Properties of ordered titanium templates covered with Au thin films for SERS applications
PublicationtCurrently, roughened metal nanostructures are widely studied as highly sensitive Raman scattering sub-strates that show application potential in biochemistry, food safety or medical diagnostic. In this workthe structural properties and the enhancement effect due to surface enhanced Raman scattering (SERS) ofhighly ordered nano-patterned titanium templates covered with thin (5–20 nm) gold films are reported.The templates are formed...
-
Equal Baseline Camera Array—Calibration, Testbed and Applications
PublicationThis paper presents research on 3D scanning by taking advantage of a camera array consisting of up to five adjacent cameras. Such an array makes it possible to make a disparity map with a higher precision than a stereo camera, however it preserves the advantages of a stereo camera such as a possibility to operate in wide range of distances and in highly illuminated areas. In an outdoor environment, the array is a competitive alternative...
-
Video Classification Technology in a Knowledge-Vision-Integration Platform for Personal Protective Equipment Detection: An Evaluation
PublicationThis work is part of an effort for the development of a Knowledge-Vision Integration Platform for Hazard Control (KVIP-HC) in industrial workplaces, adaptable to a wide range of industrial environments. This paper focuses on hazards resulted from the non-use of personal protective equipment (PPE), and examines a few supervised learning techniques to compose the proposed system for the purpose of recognition of three protective...
-
Three levels of fail-safe mode in MPI I/O NVRAM distributed cache
PublicationThe paper presents architecture and design of three versions for fail-safe data storage in a distributed cache using NVRAM in cluster nodes. In the first one, cache consistency is assured through additional buffering write requests. The second one is based on additional write log managers running on different nodes. The third one benefits from synchronization with a Parallel File System (PFS) for saving data into a new file which...
-
EXPERIMENTAL AND NUMERICAL INVESTIGATIONS OF CONCRETE BEHAVIOUR AT MESO-LEVEL DURING QUASI-STATIC SPLITTING TENSION
PublicationThe paper describes experimental and numerical results of quasi-static splitting tensile tests on concrete specimens at meso-scale level. The loading strip was made of plywood or steel. Fracture in concrete was detected at the aggregate level by means of three non-destructive methods: 3D x-ray micro-computed tomography, 2D scanning electron microscope and manual 2D digital microscope. The discrete element method was used to directly...
-
Improving Accuracy of Respiratory Rate Estimation by Restoring High Resolution Features With Transformers and Recursive Convolutional Models
PublicationNon-contact evaluation of vital signs has been becoming increasingly important, especially in light of the COVID- 19 pandemic, which is causing the whole world to examine people’s interactions in public places at a scale never seen before. However, evaluating one’s vital signs can be a relatively complex procedure, which requires both time and physical contact between examiner and examinee. These re- quirements limit the number...
-
Processing, Performance Properties, and Storage Stability of Ground Tire Rubber Modified by Dicumyl Peroxide and Ethylene-Vinyl Acetate Copolymers
PublicationIn this paper, ground tire rubber was modified with dicumyl peroxide and a variable content (in the range of 0–15 phr) of ethylene-vinyl acetate copolymers characterized by different vinyl acetate contents (in the range of 18–39 wt.%). Modification of ground tire rubber was performed via an auto-thermal extrusion process in which heat was generated during internal shearing of the material inside the extruder barrel. The processing,...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
A High-Efficient Measurement System With Optimization Feature for Prototype CMOS Image Sensors
PublicationIn this paper, a gray-scale CMOS image sensor (CIS) characterization system with an optimization feature has been proposed. By using a very fast and precise control of light intensity, based on the pulsewidth-modulation method, it is avoided to measure the illuminance every time. These features accelerate the multicriteria CIS optimization requiring many thousands of measurements. The system throughput is 2.5 Gb/s, which allows...
-
Estimation of DC motor parameters using a simple CMOS camera
PublicationDifferent components of control systems for mobile robots are based on dynamic models. In low-cost solutions such a robot is wheeled and equipped with DC motors, which have to be included in the model of the robot. The model is fairly simple but determination of its parameters needs not to be easy. For instance, DC motor parameters are typically identified indirectly using suitable measurements, concerning engine voltage, current,...
-
Low-Power Receivers for Wireless Capacitive Coupling Transmission in 3-D-Integrated Massively Parallel CMOS Imager
PublicationThe paper presents pixel receivers for massively parallel transmission of video signal between capacitive coupled integrated circuits (ICs). The receivers meet the key requirements for massively parallel transmission, namely low-power consumption below a single μW, small area of less than 205 μm2, high sensitivity better than 160 mV, and good immunity to crosstalk. The receivers were implemented and measured in a 3-D IC (two face-to-face...
-
Discrete element method simulations of fracture in concrete under uniaxial compression based on its real internal structure
PublicationThe paper describes experimental and numerical results of concrete fracture under quasi-static uniaxial compression. Experimental uniaxial compression tests were performed on concrete cubic specimens. Fracture in concrete was detected at the aggregate level by means of three non-destructive methods: three-dimensional X-ray microcomputed tomography, two-dimensional scanning electron microscope and manual two-dimensional digital...
-
EXAMINING INFLUENCE OF VIDEO FRAMERATE AND AUDIO/VIDEO SYNCHRONIZATION ON AUDIO-VISUAL SPEECH RECOGNITION ACCURACY
PublicationThe problem of video framerate and audio/video synchronization in audio-visual speech recogni-tion is considered. The visual features are added to the acoustic parameters in order to improve the accuracy of speech recognition in noisy conditions. The Mel-Frequency Cepstral Coefficients are used on the acoustic side whereas Active Appearance Model features are extracted from the image. The feature fusion approach is employed. The...
-
EXAMINING INFLUENCE OF VIDEO FRAMERATE AND AUDIO/VIDEO SYNCHRONIZATION ON AUDIO-VISUAL SPEECH RECOGNITION ACCURACY
PublicationThe problem of video framerate and audio/video synchronization in audio-visual speech recognition is considered. The visual features are added to the acoustic parameters in order to improve the accuracy of speech recognition in noisy conditions. The Mel-Frequency Cepstral Coefficients are used on the acoustic side whereas Active Appearance Model features are extracted from the image. The feature fusion approach is employed. The...
-
Improving depth maps of plants by using a set of five cameras
PublicationObtaining high-quality depth maps and disparity maps with the use of a stereo camera is a challenging task for some kinds of objects. The quality of these maps can be improved by taking advantage of a larger number of cameras. The research on the usage of a set of five cameras to obtain disparity maps is presented. The set consists of a central camera and four side cameras. An algorithm for making disparity maps called multiple...
-
Advanced Monte Carlo simulator of the polarization-sensitive optical coherence tomography systems
PublicationSimulations of the optical coherence tomography (OCT) systems using the Monte Carlo method is a widely explored research area. However, there are several difficulties that need to be overcome in order to properly model the OCT imaging with the Monte Carlo algorithm. First of all, the temporal and the spatial coherence of the scattered light need to be considered, since OCT is based on the interference phenomenon. For the same reason,...
-
A PROPOSAL FOR ONE-IMAGE PHOTOGRAMMETRY SYSTEM FOR MEASURING THE CLEARANCE DISTANCE. CASE STUDY
PublicationMeasurement of the clearance distance (both in the context of the rail and road) is one of the current and increasingly discussed topics in the context of photogrammetric and image processing (computer vision) methods. The article presents a description of a simple and rapid method of measure the clearance distance between the obstacles by using one-image photogrammetry. The proposed method was tested for the railway, tram and...
-
The Proposition of an Automated Honing Cell with Advanced Monitoring
PublicationHoning of holes allows for small shape deviation and a low value of a roughness profile parameter, e.g., Ra parameter. The honing process heats the workpiece and raises its temperature. The increase in temperature causes thermal deformations of the honed holes. The article proposes the construction of a honing cell, containing in addition to CNC honing machine: thermographic camera, sound intensity meter, and software for collecting...
-
Fabrication of anti-corrosion nitrogen doped graphene oxide coatings by electrophoretic deposition
PublicationThis work assesses anti-corrosion properties of graphene and N-doped graphene coatings deposited on copper by an electrophoretic method. Graphene oxide (GO) precursor was synthesized by an improved Hummers' method, whereas N-doping was performed hydrothermally in the presence of ammonia. After nitrogenation, doped graphene oxide samples (NGO) contained a reduced amount of oxygen and about 9% w/w nitrogen as pyridinic, pyrrole,...
-
MRI-Derived Subcutaneous and Visceral Adipose Tissue Reference Values for Children Aged 6 to Under 18 Years
PublicationThe assessment of body composition in pediatric population is essential for proper nutritional support during hospitalization. However, currently available methods have limitations. This study aims to propose a novel approach for nutrition status assessment and introduce magnetic resonance imaging (MRI)-derived subcutaneous and visceral fat normative reference values. A total of 262 healthy subjects aged from 6 to 18 years underwent...
-
Pressure drop related to flow maldistribution in a model minichannel plate heat exchanger
PublicationThe paper describes the issues related to the pressure drop that accompanies the phenomenon of maldistribution of working fluid between the channels of a model minichannel plate heat exchanger. The research concerns a single exchanger's plate containing 51 (in every geometry) parallel rectangular minichannels of hydraulic diameters 461 µm, 571 µm, 750 µm and 823 µm. In addition, the more complex geometry has been investigated,...
-
Mechanical and fracture properties of concrete reinforced with recycled and industrial steel fibers using Digital Image Correlation technique and X-ray micro computed tomography
PublicationPaper presents investigation of fracture phenomenon in plain concrete and in concrete reinforced with both recycled steel fibers (RSF) and industrial steel fibers (ISF). The wedge splitting test (WST), which enables stable crack propagation for quasi-brittle materials, was carried out on 75 75 75 mm cube samples. Initially, fracture process zone development was investigated only on the surface of samples using Digital Image Correlation...
-
Normalization of face illumination using basic knowledge and information extracted from a single image
PublicationThis paper presents a method for face image normalization that can be applied to the extraction of illumination invariant facial features or used to remove bad lighting effects and produce high-quality, photorealistic results. Most of the existing approaches concentrate on separating the constant albedo from the variable light intensity; that concept, however, is based on the Lambertian model, which fails in the presence of specularities...