Filters
total: 30366
-
Catalog
displaying 1000 best results Help
Search results for: IMAGE CLASSIFICATION , TRAFFIC LIGHT RECOGNITION , VIDEO CLASSIFICATION , FSA METHOD , SHIFTING WINDOW
-
Supervised Classification Problems–Taxonomy of Dimensions and Notation for Problems Identification
Publication -
An approach to machine classification based on stacked generalization and instance selection
Publication -
Role of various parametres in automatic classification of musical instrument sound.
PublicationArtkuł dotyczy problemu automatycznej klasyfikacji dźwięków instrumentów muzycznych, w tym głównie wpływu indywidualnych parametrów na proces automatycznego rozpoznawania instrumentów. Parametryzacja wykorzystuje wdirmo Fourierowskie i analizę czasową dźwięków do formowania 14 i 62-parametrowych wektorów cech dystynktywnych. Autorzy porównują jakość rozpoznawania i rozróźnialność instrumentów. Przy ocenach tego typu stosowano drzewa...
-
Basic evaluation of limb exercises based on electromyography and classification methods
PublicationSymptoms caused by cerebral palsy or stroke deprive a person partially or even completely of his ability to move. Nowadays we can observe more technologically advanced rehabilitation devices which incorporate biofeedback into the process of rehabilitation of such people. However, there is still a lack of devices that would analyse, assess, and control (independently or with limited support) specialised movement exercises. Here...
-
Meat freshness classification using ultra-fast gas chromatography
PublicationMeat constitutes an important component of human diet. In order to ensure that it is safe to consume, it is important to be able to determine whether a particular sample is fresh. To this end, an analysis of the headspace of pork, beef, and poultrywas performed over a period of seven days using ultra-fast gas chromatography. Compounds that may possibly be used as indicators of spoilage were identified. Based on the obtained results...
-
Otopy Classification of Gradient Compact Perturbations of Identity in Hilbert Space
PublicationWe prove that the inclusion of the space of gradient local maps into the space of all local maps from Hilbert space to itself induces a bijection between the sets of the respective otopy classes of these maps, where by a local map we mean a compact perturbation of identity with a compact preimage of zero.
-
Design Elements of Affect Aware Video Games
PublicationIn this paper issues of design and development process of affect-aware video games are presented. Several important design aspects of such games are pointed out. A concept of a middleware framework is proposed that separates the development of affect-aware video games from emotion recognition algorithms and support from input sensors. Finally, two prototype affect-aware video games are presented that conform to the presented architecture...
-
Pursuing the Deep-Learning-Based Classification of Exposed and Imagined Colors from EEG
PublicationEEG-based brain-computer interfaces are systems aiming to integrate disabled people into their environments. Nevertheless, their control could not be intuitive or depend on an active external stimulator to generate the responses for interacting with it. Targeting the second issue, a novel paradigm is explored in this paper, which depends on a passive stimulus by measuring the EEG responses of a subject to the primary colors (red,...
-
Performance Evaluation of the Parallel Codebook Algorithm for Background Subtraction in Video Stream
PublicationA background subtraction algorithm based on the codebook approach was implemented on a multi-core processor in a parallel form, using the OpenMP system. The aim of the experiments was to evaluate performance of the multithreaded algorithm in processing video streams recorded from monitoring cameras, depending on a number of computer cores used, method of task scheduling, image resolution and degree of image content variability....
-
Deep learning based thermal image segmentation for laboratory animals tracking
PublicationAutomated systems for behaviour classification of laboratory animals are an attractive alternative to manual scoring. However, the proper animals separation and tracking, especially when they are in close contact, is the bottleneck of the behaviour analysis systems. In this paper, we propose a method for the segmentation of thermal images of laboratory rats that are in close contact during social behaviour tests. For this, we are...
-
Video traffic data - Interchanges Wolnosci (86 - 94)
Open Research DataThe data includes video traffic data registered with 3 video cameras at entry or exit lanes of the Wolnosci interchange within 86 national road in Poland (interchange of national roads 86 and 94 ), located in the Silesian Agglomeration). The data covers the one days: 22.05.201 (national road 86).
-
Segmentation Quality Refinement in Large-Scale Medical Image Dataset with Crowd-Sourced Annotations
PublicationDeployment of different techniques of deep learning including Convolutional Neural Networks (CNN) in image classification systems has accomplished outstanding results. However, the advantages and potential impact of such a system can be completely negated if it does not reach a target accuracy. To achieve high classification accuracy with low variance in medical image classification system, there is needed the large size of the...
-
On a systematic perspective on risk for formal safety assessment (FSA)
Publication -
A Survey of Vehicular Network Systems for Road Traffic Management
PublicationIn this survey, we analyze the proposals of vehicular communication systems in the context of road traffic management. Starting with the definition of communications between vehicles (V2V), vehicles-to-infrastructure (V2I) and vehicles-to-everything (V2X), we first focus on the requirements and current standards for the Intelligent Transport Systems (ITS), including the maximum communication delay, the communication range and the...
-
Novel Vision Monitoring Method Based on Multi Light Points for Space-Time Analysis of Overhead Contact Line Displacements
PublicationThe article presents an innovative vision monitoring method of overhead contact line (OCL) displacement, which utilizes a set of LED light points installed along it. A light point is an, LED fed from a battery. Displacements of the LED points, recorded by a camera, are interpreted as a change of OCL shape in time and space. The vision system comprises a camera, properly situated with respect to the OCL, which is capable of capturing...
-
Classification and fingerprinting of kiwi and pomelo fruits by multivariate analysis of chromatographic and spectroscopic data
PublicationThe fingerprinting capacity of two analytical techniques, HPLC and UV-Vis spectroscopy in the case of fruits samples (kiwi and pomelo) has been investigated. The multivariate exploratory techniques were used for sample discrimination according to the fruit species and subspecies. The combination of principal component analysis with linear discriminant analysis is opening new directions in the fingerprinting analysis. The classifications...
-
Music Genre Recognition in the Rough Set-Based Environment
PublicationThe aim of this paper is to investigate music genre recognition in the rough set-based environment. Experiments involve a parameterized music data-base containing 1100 music excerpts. The database is divided into 11 classes cor-responding to music genres. Tests are conducted using the Rough Set Exploration System (RSES), a toolset for analyzing data with the use of methods based on the rough set theory. Classification effectiveness...
-
Efficiency comparison of selected endoscopic video analysis algorithms
PublicationIn the paper, selected image analysis algorithms were examined and compared in the task of identifying informative frames, blurry frames, colorectal cancer and healthy tissue on endoscopic videos. In order to standardize the tests, the algorithms were modified by removing from them parts responsible for the classification, and replacing them with Support Vector Machines and Artificial Neural Networks. The tests were performed in...
-
Video traffic data - Interchange Karczemki (S6-501)
Open Research DataThe data includes video traffic data registered with 5 video cameras at weaving area (weaving section type A) of the Karczemki interchange within S6 expressway in Poland (interchange of expressway S6 and regional road 501), located in the Tri-City Agglomeration . The data covers the one day: 10.10.2017 (expressway S6).
-
Gain deficit effect in the fractional delay filter design by the window method
PublicationMetoda okien jest sposobem szybkiego i skutecznego projektowania filtrów ułamkowoopóźniających. Jednakże wzmocnienie tak zaprojektowanego filtru różni się od zakładanej wartości idealnej. To zjawisko, nazywane deficytem wzmocnienia, negatywnie wpływa na jakoś projektowanego filtru. Artykuł poświęcono wynikom badań oraz metodom korekcji tego problemu. Omówiono wpływ współczynnika korekcji deficytu wzmocnienia na charakterystykę...
-
A method of selecting light sources from night satellite scenes
PublicationSatellite images carries a lot of data. Very sophisticated methods of analyses may reveal very complicated nature of the observed objects. In case of night images, lights play the role of information sources. In this paper we would like to present results of the research aimed to describe light sources from satellite night images by providing description of their luminosity. The authors point source imaging data from the satellite...
-
Multi-task Video Enhancement for Dental Interventions
PublicationA microcamera firmly attached to a dental handpiece allows dentists to continuously monitor the progress of conservative dental procedures. Video enhancement in video-assisted dental interventions alleviates low-light, noise, blur, and camera handshakes that collectively degrade visual comfort. To this end, we introduce a novel deep network for multi-task video enhancement that enables macro-visualization of dental scenes. In particular,...
-
Maritime traffic situation awareness analysis via high-fidelity ship imaging trajectory
PublicationSituation awareness provides crucial yet instant information to maritime traffic participants, and significant attentions are paid to implement traffic situation awareness task via various maritime data source (e.g., automatic identification system, maritime surveillance video, radar, etc.). The study aims to analyze traffic situation with the support of ship imaging trajectory. First, we employ the dark channel prior model to...
-
Recognition of two-phase flow patterns with the use of dynamic image analysis
Publication -
MSIS sonar image segmentation method based on underwater viewshed analysis and high-density seabed model
PublicationHigh resolution images of Mechanically Scanned Imaging Sonars can bring detailed representation of underwater area if favorable conditions for acoustic signal to propagate are provided. However to properly asses underwater situation based solely on such data can be challenging for less than proficient interpreter. In this paper we propose a method to enhance interpretative potential of MSIS image by dividing it in to subareas depending...
-
Comparison of two methods of sound extraction from guitar string video recordings
PublicationA comparison of two sound extraction methods from guitar string video recordings is presented in the paper. A brief overview of highframe rate camera technology and possible applications are included. The method using the image analysis from two such cameras is presented. The cameras are placed at the angle of 90 degrees for recording the image in three planes. The results achieved...
-
IMAGE CORRELATION AS A TOLL FOR TRACKING FACIAL CHANGES CAUSING BY EXTERNAL STIMULI
PublicationExpressions of the human face bring a lot of information, which are a valuable source in the areas of computer vision, remote sensing and affective computing. For years, by analyzing the movement of the skin and facial muscles scientists are trying to create the perfect tool, based on image analysis, allowing the recognition of emotional states of human beings. To create a reliable algorithm, it is necessary to explore and examine...
-
Ecotoxicity and chemical sediment data classification by the useof self-organising maps
PublicationArtykuł dotyczy przedstawiania nowej interpretacji szacowania jakości osadów. To oryginalne podejście bada powiązania między parametrami ekotoksyczności (ostrej i chronicznej) i składnikami chemicznymi (zanieczyszczenia takie jak polichlorowane bifenyle, pestycydy, wielopierścieniowe węglowodory aromatyczne, metale ciężkie) próbek osadów Jeziora Turawskiego (Polska) poprzez zastosowanie samoorganizujących się map (SOM) wobec badanego...
-
Collecting and classification web data for business using a web farming system
PublicationPraca prezentuje system typu Web Farming oraz aspekty związane z jego działaniem.
-
An Approach to Imbalanced Data Classification Based on Instance Selection and Over-Sampling
Publication -
Impact of Clustering on a Synthetic Instance Generation in Imbalanced Data Streams Classification
Publication -
Stacking and rotation-based technique for machine learning classification with data reduction
Publication -
Spam classification methods besed on users e-mail communication graphs
PublicationW artykule poddano analizie grafy zbudowane w oparciu o logi serwerów pocztowych. Węzły grafów reprezentują nadawców i odbiorców wiadomości e-mail natomiast krawędzie przedstawiają procesy wymiany wiadomości e-mail. Analiza grafów pozwala na znalezienie korelacji pomiędzy topologią grafów a relacjami pomiędzy użytkownikami serwisu pocztowego. W oparciu o te relacje zaproponowano algorytm klasyfikujący wymieniane wiadomości e-mail...
-
Identification and classification model of the quality perception determinants and tourist services attributes
PublicationW niniejszym rozdziale zaprezentowano model identyfikacji oraz klasyfikacji zarówno determinant percepcji jakości jak i cech charakterystycznych dla usług turystycznych. Wykorzystano w tym celu zarówno cechy charakterystyczne dla usług dowolnego rodzaju zaadaptowane na potrzeby usług turystycznych jak i te które są specyficzne wyłącznie dla tej branży.
-
Detection and classification of gaseous compounds by solid electrolyte cyclic voltammetry sensors
PublicationW pracy omówiono właściwości i ostatnie wyniki badań dotyczące czujników elektrokatalitycznych.
-
Empirical analysis of tree-based classification models for customer churn prediction
PublicationCustomer churn is a vital and reoccurring problem facing most business industries, particularly the telecommunications industry. Considering the fierce competition among telecommunications firms and the high expenses of attracting and gaining new subscribers, keeping existing loyal subscribers becomes crucial. Early prediction of disgruntled subscribers can assist telecommunications firms in identifying the reasons for churn and...
-
Dangerous sound event recognition using Support Vector Machine classifiers
PublicationA method of recognizing events connected to danger based on their acoustic representation through Support Vector Machine classification is presented. The method proposed is particularly useful in an automatic surveillance system. The set of 28 parameters used in the classifier consists of dedicated parameters and MPEG-7 features. Methods for parameter calculation are presented, as well as a design of SVM model used for classification....
-
Mariusz Kaczmarek dr hab. inż.
PeopleReceived M.Sc., Eng. in Electronics in 1995 from Gdansk University of Technology, Ph.D. in Medical Electronics in 2003 and habilitation in Biocybernetics and Biomedical Engineering in 2017. He was an investigator in about 13 projects receiving a number of awards, including four best papers, practical innovations (7 medals and awards) and also the Andronicos G. Kantsios Award and Siemens Award. Main research activities: the issues...
-
Comparison of Traffic Flow Models with Real Traffic Data Based on a Quantitative Assessment
PublicationThe fundamental relationship of traffic flow and bivariate relations between speed and flow, speed and density, and flow and density are of great importance in transportation engineering. Fundamental relationship models may be applied to assess and forecast traffic conditions at uninterrupted traffic flow facilities. The objective of the article was to analyze and compare existing models of the fundamental relationship. To that...
-
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...
-
Video traffic data - Interchange Slowackiego (S8-Slowackiego), Poland
Open Research DataThe data includes video traffic data registered with 4 video cameras at entry or exit lanes of the Slowackiego interchange within S8 expressway in Poland (interchange of expressway S8 and Slowackiego street), located in the Warsaw Agglomeration. The data covers the one day: 10-11.05.2017 (expressway S8).
-
Video traffic data - Interchange Tychy (1-44), Poland
Open Research DataThe data includes video traffic data registered with 8 video cameras at weaving area (weaving section type A) of the Tychy interchange within national road 1 in Poland (interchange of national roads 1 and 44), located in the Silesian Agglomeration. The data covers the two days:13-14.09.2017.
-
Video traffic data - Interchange Broniewskiego (S8-Broniewskiego), Poland
Open Research DataThe data includes video traffic data registered with 4 video cameras at entry or exit lanes of the Broniewskiego interchange within S8 expressway in Poland (interchange of expressway S8 and Broniewskiego street), located in the Warsaw Agglomeration. The data covers the two days: 10-11.05.2017 (expressway S8).
-
A Method and Device for 3D Recognition of Cutting Edge Micro Geometry
PublicationA very useful method was successfully applied in the investigation of tools for machining wood and wood based composites. It allows scanning of the cutting edge micro geometry in three dimensions and reproducing it in a virtual space as a 3D surface. The application of the method opens new possibilities of studying tool wear by scanning, including the calculation of volume loss and other analysis of tool wedge geometry along and...
-
seafloor characterisation combined approach using multibeam sonar echo signal processing and image analysis
PublicationThe authors propose the approach to seafloor characterisation which relies on the combined, concurrent use of two different techniques: (i) multibeam sonar image analysis and (ii) multibeam seabed echoes processing. The first technique is based on constructing the grey-level sonar images of the seabed extracted from the echoes received in the consecutive soundings. Then, the set of parameters describing the local region of sonar...
-
Automated Classifier Development Process for Recognizing Book Pages from Video Frames
PublicationOne of the latest developments made by publishing companies is introducing mixed and augmented reality to their printed media (e.g. to produce augmented books). An important computer vision problem that they are facing is classification of book pages from video frames. The problem is non-trivial, especially considering that typical training data is limited to only one digital original per book page, while the trained classifier...
-
Video DATA - Traffic generation modeling for discount shops - Rakoczego Street
Open Research DataThe data includes video traffic data (vehicles, pedestrians, cyclists) registered at 21 Rakoczego street in Gdansk. The data covers the day 01.10.2020 at 6:00-10:00. The video camera was installed niearby the parking area belonging to the discount store Lidl. The data obtained was used in analysis, providing information about the modal split and the...
-
Karol Flisikowski dr inż.
PeopleKarol Flisikowski works as Associate Professor at the Department of Statistics and Econometrics, Faculty of Management and Economics, Gdansk University of Technology. He is responsible for teaching descriptive and mathematical statistics (in Polish and English), as well as scientific research in the field of social statistics. He has been a participant in many national and international conferences, where he has presented the results...
-
Estimation of object size in the calibrated camera image = Estymacja rozmiaru obiektów w obrazach ze skalibrowanej kamery
PublicationIn the paper, a method of estimation of the physical sizes of the objects tracked by the camera is presented. First, the camera is calibrated, then the proposed algorithm is used to estimate the real width and height of the tracked moving objects. The results of size estimation are then used for classification of the moving objects. Two methods of camera calibration are compared, test results are presented and discussed. The proposed...
-
Visual Lip Contour Detection for the Purpose of Speech Recognition
PublicationA method for visual detection of lip contours in frontal recordings of speakers is described and evaluated. The purpose of the method is to facilitate speech recognition with visual features extracted from a mouth region. Different Active Appearance Models are employed for finding lips in video frames and for lip shape and texture statistical description. Search initialization procedure is proposed and error measure values are...