Wyniki wyszukiwania dla: object detection
-
The Effectiveness of Using a Pretrained Deep Learning Neural Networks for Object Classification in Underwater Video
Publikacja -
Experimental evaluation of high frequency side scan sonar as object search and identification tool
PublikacjaPraca prezentuje wyniki badań laboratoryjnych sonaru bocznego jako narzędzia dla pojazdu podwodnego, służącego do poszukiwań i identyfikacji obiektów leżących na dnie, w bliskich odległościach.
-
The partial-order tree: a new structure for indexing on complex attributes in object-oriented databases
Publikacja -
Scattering From a Cylindrical Object of Arbitrary Cross Section With the Use of Field Matching Method
PublikacjaA simple and intuitive solution to scattering problems in shielded and open structures is presented. The main idea of the analysis is based on the direct field matching technique involving the usage of projection of the fields at the boundary on a fixed set of orthogonal basis functions. Different convex shapes and various obstacle materials are considered to verify the validity of the method in open and closed structures. The...
-
Networked Object Monitor - A distributed system for monitoring, diagnostics and control of complex industrial facilities
PublikacjaRozwój mobilności i technologii internetowych, a także globalizacji gospodarki światowej, uwzględniający kluczowe aspekty zarządzania przepływem informacji, otworzył zupełnie nowe możliwości opracowywania i konstruowania innowacyjnych rozwiązań technicznych. Z taką myślą powstał prototyp Sieciowego Monitora Obiektu, aplikacji umożliwiającej nie tylko ciągłą kontrolę parametrów obiektów przemysłowych i biznesowych, ale również zarządzanie...
-
Virtual Engineering Object / Virtual Engineering Process: A specialized form of Cyber Physical System for Industrie 4.0
PublikacjaThis paper reviews the theories, parallels and variances between Virtual Engineering Object (VEO) / Virtual Engineering Process (VEP) and Cyber Physical System (CPS). VEO and VEP is an experience based knowledge representation of engineering objects and processes respectively. Cyber–physical systems (CPSs) are the next generation of engineered systems in which computing, communication, and control technologies are tightly integrated....
-
Real-Time Facial Features Detection from Low Resolution Thermal Images with Deep Classification Models
PublikacjaDeep networks have already shown a spectacular success for object classification and detection for various applications from everyday use cases to advanced medical problems. The main advantage of the classification models over the detection models is less time and effort needed for dataset preparation, because classification networks do not require bounding box annotations, but labels at the image level only. Yet, after passing...
-
Diagnostics of high-voltage varistor quality using resonant ultrasound spectroscopy
PublikacjaResonant spectroscopy is an effective nondestructive testing method focused on defects detection in tested objects. Resonance spectrum contains an information about the mechanical properties and particularly about the structural homogeneity of the whole object. A swept frequency method has been used to measure the selected resonant frequencies range. The system for measurement of resonant ultrasound spectroscopy of high-voltage...
-
Tracking Moving Objects in Video Surveillance Systems with Kalman and Particle Filters – A Practical Approach
PublikacjaThis Chapter focuses on the first type of object tracking algorithms, namely on Kalman and particle filters. A theory of these algorithms may be found in many publications, there are also reports on implementation of these approaches to object tracking in video. However, developers of VCA systems still face two important problems. The first one is related to obtaining accurate measurements of positions and sizes of the tracked...
-
Fully Automated AI-powered Contactless Cough Detection based on Pixel Value Dynamics Occurring within Facial Regions
PublikacjaIncreased interest in non-contact evaluation of the health state has led to higher expectations for delivering automated and reliable solutions that can be conveniently used during daily activities. Although some solutions for cough detection exist, they suffer from a series of limitations. Some of them rely on gesture or body pose recognition, which might not be possible in cases of occlusions, closer camera distances or impediments...
-
Integrating Experience-Based Knowledge Representation and Machine Learning for Efficient Virtual Engineering Object Performance
PublikacjaMachine learning and Artificial Intelligence have grown significant attention from industry and academia during the past decade. The key reason behind interest is such technologies capabilities to revolutionize human life since they seamlessly integrate classical networks, networked objects and people to create more efficient environments. In this paper, the Knowledge Representation technique of Set of Experience...
-
THE COST ANALYSIS OF CORROSION PROTECTION SOLUTIONS FOR STEEL COMPONENTS IN TERMS OF THE OBJECT LIFE CYCLE COST
PublikacjaSteel materials, due to their numerous advantages - high availability, easiness of processing and possibility of almost any shaping are commonly applied in construction for carrying out basic carrier systems and auxiliary structures. However, the major disadvantage of this material is its high corrosion susceptibility, which depends strictly on the local conditions of the facility and the applied type of corrosion protection system....
-
Video Semantic Analysis Framework based on Run-time Production Rules - Towards Cognitive Vision
PublikacjaThis paper proposes a service-oriented architecture for video analysis which separates object detection from event recognition. Our aim is to introduce new tools to be considered in the pathway towards Cognitive Vision as a support for classical Computer Vision techniques that have been broadly used by the scientific community. In the article, we particularly focus in solving some of the reported scalability issues found in current...
-
Polarization-sensitive optical coherence tomography for ceramic materials inspection
PublikacjaCeramics production is looking for a fast, reliable and non-destructive method that can be implemented on site for defect detection and analysis. In this paper we present polarization-sensitive optical coherence tomography (PS-OCT) as a method for defect inspection. Proposed extensions to standard OCT provide additional information for complete characterization of tested object. We compare OCT and microscope imaging that can easily...
-
Języki skonstruowane jako obiekt badań współczesnej interlingwistyki [Constructed Languages as an Object of Study in Contemporary Interlinguistics]
Publikacja -
Designing of an effective structure of system for the maintenance of a technical object with the using information from an artificial neural network
Publikacja -
Electromagnetic plane wave scattering from a cylindrical object with an arbitrary cross section using a hybrid technique
PublikacjaA hybrid technique combining finite-element and mode-matching methods for the analysis of scattering problems in open and closed areas is presented. The main idea of the analysis is based on the utilization of the finite-element method to calculate the post impedance matrix and combine it with external excitation. The discrete analysis, which is the most time- and memory-consuming, is limited here only to the close proximity of...
-
The Innovative Faculty for Innovative Technologies
PublikacjaA leaflet describing Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology. Multimedia Systems Department described laboratories and prototypes of: Auditory-visual attention stimulator, Automatic video event detection, Object re-identification application for multi-camera surveillance systems, Object Tracking and Automatic Master-Slave PTZ Camera Positioning System, Passive Acoustic Radar,...
-
Numerical modeling of GPR field in damage detection of a reinforced concrete footbridge
PublikacjaThe paper presents a study on the use of the ground penetrating radar (GPR) method in diagnostics of a footbridge. It contains experimental investigations and numerical analyses of the electromagnetic field propagation using the finite difference time domain method (FDTD). The object of research was a reinforced concrete footbridge over a railway line. The calculations of the GPR field propagation were performed on a selected cross-section...
-
A New Adaptive Method for the Extraction of Steel Design Structures from an Integrated Point Cloud
Dane BadawczeA new automatic and adaptive algorithm for edge extraction from a random point cloud was developed and presented herein. The proposed algorithm was tested using real measurement data. The developed algorithm is able to realistically reduce the amount of redundant data and correctly extract stable edges representing the geometric structures of a studied...
-
Melanoma skin cancer detection using mask-RCNN with modified GRU model
PublikacjaIntroduction: Melanoma Skin Cancer (MSC) is a type of cancer in the human body; therefore, early disease diagnosis is essential for reducing the mortality rate. However, dermoscopic image analysis poses challenges due to factors such as color illumination, light reflections, and the varying sizes and shapes of lesions. To overcome these challenges, an automated framework is proposed in this manuscript. Methods: Initially, dermoscopic...
-
Suppression of distortions in signals received from Doppler sensor for vehicle speed measurement
PublikacjaDoppler sensors are commonly used for movement detection and speed measurement. However, electromagnetic interference and imperfections in sensor construction result in degradation of the signal to noise ratio. As a result, detection of signals reflected from moving objects becomes problematic. The paper proposes an algorithm for reduction of distortions and noise in the signal received from a simple, dual-channel type of a Doppler...
-
Reducing the Uncertainty of the Moving Object Location Measurement with the Method of Quasi-Multiple Measurement in GNSS Technology in Symmetrical Arrangement
Publikacja -
Wpływ kształtu otwartego obiektu ferromagnetycznego na pole magnetyczne.Influence of shape of open ferromagnetic object on magnetic field.
PublikacjaObiekt o właściwościach ferromagnetycznych znajdujący się w ziemskim polu magnetycznym zaburza równomierność tego pola. Przestrzenny rozkład zaburzenia pola zależy od wielu czynników, w tym między innymi od rozmiarów i kształtu obiektu, od jego właściwości ferro-magnetycznych i od położenia względem wektora ziemskiego pola magnetycznego. Na podstawie pomiaru rozkładu pola magnetycznego wokół obiektu można dokonać lokalizacji i...
-
Model-Driven Testing of Real-Time Embedded Systems - From Object Oriented towards Function Oriented Development
PublikacjaMBD
-
Reducing the Uncertainty of the Moving Object Location Measurement with the Method of Quasi-Multiple Measurement in GNSS Technology in Symmetrical Arrangement
PublikacjaThe article presents a solution to the problem of limited accuracy of dynamic measurements performed with GNSS receivers. The proposed measurement method is a response to the needs related to the assessment of the measurement uncertainty of the position of the track axis of the rail transport line. However, the problem of reducing the measurement uncertainty is universal for many different situations where high accuracy of positioning...
-
Acoustic Processor of the Mine Countermeasure Sonar
PublikacjaThis paper presents the concept of an acoustic processor of the mine countermeasure sonar. Developed at the Department of Marine Electronics Systems, Gdansk University of Technology, the acoustic processor is an element of the MG-89, an underwater acoustic station. The focus of the article is on the modules of the processor. They are responsible for sampling analogue signals and implementing the algorithms controlling the measurement...
-
Instance segmentation of stack composed of unknown objects
PublikacjaThe article reviews neural network architectures designed for the segmentation task. It focuses mainly on instance segmentation of stacked objects. The main assumption is that segmentation is based on a color image with an additional depth layer. The paper also introduces the Stacked Bricks Dataset based on three cameras: RealSense L515, ZED2, and a synthetic one. Selected architectures: DeepLab, Mask RCNN, DEtection TRansformer,...
-
Vehicle detector training with minimal supervision
PublikacjaRecently many efficient object detectors based on convolutional neural networks (CNN) have been developed and they achieved impressive performance on many computer vision tasks. However, in order to achieve practical results, CNNs require really large annotated datasets for training. While many such databases are available, many of them can only be used for research purposes. Also some problems exist where such datasets are not...
-
Comparison of active proximity radars for the wearable devices
PublikacjaTwo methods of object position and movement estimation in relation to the user of smart glasses were investigated. An active infrared and ultrasonic methods of the obstacle detection were presented and compared. Application of these methods depend on active transducers type (physical medium used), geometry and surface properties of detected objects and their movement direction and speed. In the article properties of both detectors...
-
An Analysis of Uncertainty and Robustness of Waterjet Machine Positioning Vision System
PublikacjaThe paper presents a new Automatic Waterjet Positioning Vision System (AWPVS) and investigates components of workpiece positioning accuracy. The main purpose of AWPVS is to precisely identify the position and rotation of a workpiece placed on a waterjet machine table. Two webcams form a basis for the system, and constitute its characteristics. The proposed algorithm comprises various image processing techniques to assure a required...
-
Acoustic Processor of the MCM Sonar
PublikacjaThis paper presents the concept of an acoustic processor of the mine countermeasure sonar. Developed at the Department of Marine Electronics Systems, Gdansk University of Technology, the acoustic processor is an element of the MG-89, a modernised underwater acoustic station. The focus of the article is on the modules of the processor. They are responsible for sampling analogue signals and implementing the algorithms controlling...
-
Vibration surveillance during ball end milling of curved flexible details on a basis of assessment of assurance of the model of real object
PublikacjaW pracy przedstawiono nową metodę nadzorowania drgań podczas frezowania zakrzywionych przedmiotów podatnych. Wykorzystano model modalny przedmiotu obrabianego, którego parametry zidentyfikowano na bazie badań doświadczalnych oraz analizy komputerowej. Zastosowanie modelu metody elementów skończonych, którego zachowanie jest zgodne z przedmiotem uformowanym w postaci cienkościennej powierzchni półwalcowej, a następnie - utworzenie...
-
Decomposition of the induced magnetism degaussing problem for fast determination of currents in demagnetization coils wrapped outside an object under arbitrary external field conditions
PublikacjaSafe passage of ships in the presence of sea mines can be ensured by limiting or reducing the ship’s magnetic footprint. For vessels with plastic hulls, the main component that requires magnetic damping is the engine. Demagnetization of such an object can be achieved by wrapping it with coils and setting the direct current appropriately. For each specific geographic location, the currents in the coils can be determined iteratively...
-
Very low resolution depth images of 200,000 poses
Dane BadawczeA dataset represents simulated images of depth sensor seeing a single human pose, performing 200,000 random gestures. The depth images as vectors of pixels are stored with ground truth positions of every relevant joint.
-
Performance analysis of power swing blocking feature in ABB 670 series impedance relays
PublikacjaThis paper presents test results of a distance protection’s PSD power swing detection feature in ABB 670 series relays. A RED670 relay was tested, which is part of the hydroelectric set protection in Żarnowiec Pumped Storage Plant. The power swing blocking feature’s performance was analysed on the basis of the results of object tests made with an Omicron digital tester. Also presented are simulation results that illustrate the...
-
Maskowanie obiektu w kształcie elipsoidy w ziemskim polu magnetycznym = Masking ellipsoid-shaped object in the Earth's magnetic field
PublikacjaW pracy wyznaczono metodą analityczną rozkład okładu prądowego uzwojeń wewnątrz obiektu o powłoce ferromagnetycznej w kształcie wydłużonej elipsoidy, który redukuje zaburzenie rozkładu pola magnetycznego na zewnątrz obiektu.
-
Bartosz Szostak mgr inż.
OsobyBartosz Szostak w 2019 r. ukończył studia inżynierskie na Politechnice Gdańskiej na kierunku Geodezja i Kartografia. W 2021 r. ukończył studia magisterskie również w dziedzinie Geodezji i Kartografii na Politechnice Gdańskiej. Tematyka jego prac dyplomowych dotyczyła uczenia maszynowego i detekcji obiektów.
-
LIDAR data from the measurement of a bridge structure along a S7 road in the vicinity of Ostróda.
Dane BadawczeThe measurement data was acquired during research aimed at utilizing LiDAR observations to assess the condition of bridge structures. The provided information originates from measurements of a road bridge located along a modernized national road near the town of Ostróda. The obtained point cloud constitutes a comprehensive set of information regarding...
-
Detecting Objects of Various Categories in Optical Remote Sensing Imagery Using Neural Networks
PublikacjaThe effective detection of objects in remote sensing images is of great research importance, so recent years have seen a significant progress in deep learning techniques in this field. However, despite much valuable research being conducted, many challenges still remain. A lot of research projects focus on detecting objects of a single category (class), while correctly detecting objects of different categories is much harder. The...
-
Multifrequency Nanoscale Impedance Microscopy (m-NIM): A novel approach towards detection of selective and subtle modifications on the surface of polycrystalline boron-doped diamond electrodes
PublikacjaIn this paper, we describe the modification of Nanoscale Impedance Microscopy (NIM), namely, a combination of contact-mode atomic force microscopy with local impedance measurements. The postulated approach is based on the application of multifrequency voltage perturbation instead of standard frequency-by-frequency analysis, which among others offers more time-efficient and accurate determination of the resultant impedance spectra...
-
Mobilny system do detekcji obiektów ferromagnetycznych z magnetometrami pompowanymi optycznie
PublikacjaW pracy przedstawiono mobilny system do detekcji obiektów ferromagnetycznych. Każdy obiekt ferromagnetyczny zaburza w swoim otoczeniu równomierność pola magnetycznego Ziemi. Zaburzenie to może być zmierzone za pomocą precyzyjnych magnetometrów. W prezentowanym mobilnym systemie zastosowano magnetometry pompowane optycznie pracujące w układzie różnicowym. W pracy opisano magnetometryczny system do detekcji obiektów ferromagnetycznych,...
-
Electromagnetic wave scattering in structures containing cylindrical object.**2005, 177 s. 119 rys. 8 tab. bibliogr. 239 poz.
Publikacja.
-
Continuous wave sonar with hyperbolic frequency modulation keyed by pseudo-random sequence
PublikacjaA CW FM type sounding signal is used in the classical solution of silent sonar. While the signal provides a relatively simple implementation of digital signal processing, and ensures good detection conditions, unfortunately, in the presence of the Doppler effect, distance measurement results tend to be wrong. This is due to the fact that the received signal’s instantaneous frequency value is dependent both on the distance to the...
-
LIDAR data from a cliff measurement conducted in the vicinity of the town of Jastrzębia Góra on the Baltic Sea coast
Dane BadawczeMeasurement data were obtained during research related to the use of LiDAR observations to assess the stability of a coastal cliff. The collected information comes from measurements conducted in the vicinity of the town of Jastrzębia Góra on the Baltic Sea coast. The acquired point cloud constitutes a comprehensive set of data regarding the geometry...
-
Zastosowanie metody równań całkowych w analizie pola ekranującego obiektów ferromagnetycznych.Application of integral equations method to shield field analysis of ferromagnetic object.
PublikacjaDuże obiekty ferromagnetyczne, jakimi są okręty, powodują zaburzenia w rozkładzie ziemskiego pola ma-gnetycznego. Dla zredukowania tego zaburzenia na okrętach umieszcza się specjalne uzwojenia, których ce-lem jest wytworzenie pola magnetycznego usuwającego zmiany wywołane obecnością ferromagnetyka w zewnętrznym polu ziemskim. Obliczania rozkładu tych uzwojeń wiąże się z koniecznością znalezienia rozkładu pola magnetycznego.Zastosowanie...
-
Sensing Direction of Human Motion Using Single-Input-Single-Output (SISO) Channel Model and Neural Networks
PublikacjaObject detection Through-the-Walls enables localization and identification of hidden objects behind the walls. While numerous studies have exploited Channel State Information of Multiple Input Multiple Output (MIMO) WiFi and radar devices in association with Artificial Intelligence based algorithms (AI) to detect and localize objects behind walls, this study proposes a novel non-invasive Through-the-Walls human motion direction...
-
AI-Powered Cleaning Robot: A Sustainable Approach to Waste Management
PublikacjaThe world is producing a massive amount of single use waste, especially plastic waste made from polymers. Such waste is usually distributed in large areas within cities, near roads, parks, forests, etc. It is a challenge to collect them efficiently. In this work, we propose a Cleaning Robot as an autonomous vehicle for waste collection, utilizing the Nvidia Jetson Nano platform for precise arm movements guided by computer...
-
Offshore benthic habitat mapping based on object-based image analysis and geomorphometric approach. A case study from the Slupsk Bank, Southern Baltic Sea
PublikacjaBenthic habitat mapping is a rapidly growing field of underwater remote sensing studies. This study provides the first insight for high-resolution hydroacoustic surveys in the Slupsk Bank Natura 2000 site, one of the most valuable sites in the Polish Exclusive Zone of the Southern Baltic. This study developed a quick and transparent, automatic classification workflow based on multibeam echosounder and side-scan sonar surveys to...
-
Analiza pola magnetycznego wewnątrz i na zewnątrz cienkościennego obiektu ferromagnetycznego = An analisis of magnetic field inside and outside thin-walled ferromagnetic object
PublikacjaAnomalia wnoszona przez obiekt ferromagnetyczny znajdujący się w ziemskim polu magnetycznym związana jest z jego namagnesowaniem stałym i indukowanym.W pracy przedstawiono wyniki badań symulacyjnych dotyczące rozkładu indukowanego pola magnetycznego wewnątrz i na zewnątrz obiektu ferromagnetycznego odpowiadającemu kadłubowi okrętu. Analizę numeryczną przeprowadzono w pakiecie OPERA 3d.