Browsing by Subject "segmentation"

Now showing 1 - 12 of 12

Access status: Open Access ,
3D spatial analysis of temporal maintenance for multi-use high-rise buildings - case study
(Wydawnictwa AGH, 2024) Mehmood, Usman; Salleh, Syahiirah; Ujang, Uznir; Azri, Suhaibah; Choon, Tan Liat
Urbanization has sparked an increase in the construction of multi-use highrise buildings which consists of commercial parcels on their lower floors and residential parcels on their higher floors. In contrast to conventional landed houses, the residents of high-rise buildings share common facilities and private parcels or spaces also differ according to ownership or use. The management and maintenance of these spaces are dependent on the ownership of the parcel where each ownership adheres to different rights, restrictions, and responsibilities (RRRs). Therefore, accurate representation and identification of those parcels affected by maintenance or renovation is crucial for assisting management bodies to improve the quality of life within a multi-use high-rise building. This study attempts to implement a temporal maintenance management for highrise building parcels within a 3D spatial database. A 3D space segmentation was done to analyze the ownership and use of space in a high-rise building. Spatial queries were also performed based on the temporal maintenance of the parcels, in addition, 3D spatial relationships were used to determine adjacent parcels that were affected by the maintenance. Thus, the implementation of temporal strata database management with an accurate 3D representation of the space can provide management bodies with concise and comprehensive information on parcels with respect to ownerships and uses.
Access status: Open Access ,
Algorytm segmentacji mikroskopowych obrazów okrzemek w preparatach z zanieczyszczeniami osadowymi
(Wydawnictwa AGH, 2009) Sekulska-Nalewajko, Joanna; Gocławski, Jarosław
In the paper a new, robust to artefacts, method of microscopic diatom image segmentation has been presented. Images are acquired in grey-levels using bright field microscopy from specimens with impurities such as dust specks, debris or sand crystals. The method assumes superposition of images from different focal planes including diatom surface ornamentation and boundaries. Diatom object contours are detected using Canny filtering and their background regions are extracted independently applying bottom hat filtering and morphological reconstruction. Contour gaps are filled by linking of all contour ends inside of individual diatom background regions. To distinguish regularly shaped objects of diatoms from artefacts, contour curvatures, symmetry axes and centres are verified for each segmented object. Directional ornamentation of diatom frastules (if present) is detected by histogram analysis of phase images inside of individual region masks.
Access status: Open Access ,
Algorytm wideodetekcji korzystający z metody obliczania przepływu optycznego
(Wydawnictwa AGH, 2011) Głowacz, Andrzej; Mikrut, Zbigniew; Pawlik, Piotr
W artykule przedstawiono koncepcję i realizację algorytmu wykrywania i zliczania pojazdów, opartego na analizie przepływu optycznego (optical flow). Porównano efektywność i czas obliczeń trzech algorytmów. Wybrano algorytm Horna-Schuncka i zastosowano go do wydzielania ruchomych obiektów. Stwierdzono, że algorytm dobrze wydziela ruchome obiekty po zastosowaniu binaryzacji stałoprogowej. Skonstruowano podstawowy algorytm detekcji i zliczania pojazdów. Przedstawiono wyniki i sformułowano plan dalszych badań.
Access status: Open Access ,
Algorytmy segmentacji obrazów barwnych w rozpoznawaniu obiektów na obrazach satelitarnych i lotniczych
(Wydawnictwa AGH, 2009) Jeżewski, Sławomir; Duch, Piotr
This paper describes influence of color space to the results of image segmentation by watershed and quadtree algorithms. The most popular color space like RGB, HSV and CIEL*a*b was analyzed. The mathematical measure of segmentation quality was presented and contrasted with the subjective human feelings. Sets of images from COREL collection and aerial images from Google were used in experiments.
Access status: Open Access ,
An algorithm to extract first and second order venation of apple-tree leaves stained for H2O2 detection
(Wydawnictwa AGH, 2010) Sekulska-Nalewajko, Joanna; Gocławski, Jarosław; Gajewska, Ewa Grażyna; Wielanek, Marzena Katarzyna
In the paper an algorithm for the extraction of first and second order leaf venation has been presented. The algorithm applies to apple tree leaves specially stained to reveal the areas of $H_{2}O_{2}$ appearing in the leaf blade as brown spots of different size and intensity. In the considered case they represent the defence reaction of planfs tissue to a bacterial infection called fire blight. Examined leaf images include visible leaf veins with colour hue and brightness similar to the $H_{2}O_{2}$ spots. They are often superimposed on leaf veins and make serious distortions for the process of their extraction. In these conditions typical algorithms for the detection of venation patterns usually fail, so a new method of primary and secondary veins detection has been proposed. The vein extraction is based on the step-wise tracking of each vein axis using polygonal linę with the line segments of fixed size. The optimal direction for each step is obtained through the minimization of the proposed cost function depending on the prediction angle. The algorithm has been written in the M-language and executed in MATLAB environment. The experiments of leaf vein tracking carried out for the series of images gave promising results accepted by the biologists.
Access status: Open Access ,
Automatyczna anotacja znaczników sztyftowych w procesie walcowania pielgrzymowego rur na zimno
(Wydawnictwa AGH, 2010) Jabłoński, Mirosław; Pociecha, Daniel
A system of automatic calculation of characteristic points in the process of tube cold rolling process has been presented. The very basic problem that has been addressed in this paper was a method of segmentation of particular regions in high resolution images i.e. reference board, tube area, and copper pin-markers. Three methods of adaptive thresholding have been examined for each type of object. Through application of computer vision algorithms duration of annotation phase has been greatly reduced in comparison to manual method.
Access status: Open Access ,
Building Semantic Segmentation Using UNet Convolutional Network on SpaceNet Public Data Sets for Monitoring Surrounding Area of Chan Chan (Peru)
(Wydawnictwa AGH, 2024) Chicchon, Miguel; Malinverni, Eva Savina; Sanità, Marsia; Pierdicca, Roberto; Colosi, Francesca; Trujillo, Francisco James León
The amount of damage to cultural heritage sites is increasing rapidly every year. This is due to inadequate heritage management and uncontrolled urban growth as well as unpredictable seismic and atmospheric events that manifest themselves in a continuously deteriorating ecosystem. Thus, applications of artificial intelligence (AI) in remote-sensing (RS) techniques (machine-learning and deep-learning algorithms) for monitoring archaeological sites have increased in recent years. This research involves the surrounding area of the archaeological site of Chan Chan in Peru in particular. An approach that is based on the use of AI algorithms for building footprint segmentation and change-detection analysis by means of RS images is proposed. It involves a UNet convolutional network based on an EfficientNet B0 to B7 encoder. The network was trained on two public data sets from SpaceNet that were based on WV2 and WV3 satellite images: SpaceNet V1 (Rio), and SpaceNet V2 (Shanghai). In the pre-processing phase, the images from the two data sets have been equalized in order to improve their quality and avoid overfitting. The building segmentation has been performed on HRV images of the study area that were downloaded from Google Earth Pro. The value that was achieved in the IoU metric was around 70% in both experiments. The purpose of this proposed methodology is to assist scientists in drafting monitoring and conservation protocols based on already-recorded data in order to prevent future disasters and hazards.
Access status: Restricted ,
Interpretacja przestrzeni porowej skał zbiornikowych z wykorzystaniem metod analizy obrazu
(Data obrony: 2011-11-03) Jarosz, Marek
Wydział Geologii, Geofizyki i Ochrony Środowiska
The paper focuses on the benefits of replacing traditional quantitative stereological measurements by using computer image analysis. During the described research, automatic reservoir rock’s pore spaces analysis was performed. The result indicates that the use of image analysis allows obtaining porosity parameter and designating more geometric parameters, which allows more accurate rocks’ description. The result states, that this type of method can be used for quantitative measurements.
Access status: Open Access ,
River Area Segmentation Using Sentinel-1 SAR Imagery with Deep-Learning Approach
(Wydawnictwa AGH, 2025) Dewi, Ni Putu Karisma; Suputra, Putu Hendra; Paramartha, A.A. Gede Yudhi; Dewi, Luh Joni Erawati; Varnakovida, Pariwate; Aryanto, Kadek Yota Ernanda
River segmentation is important in delivering essential information for environmental analytics such as water management, flood/disaster management, observations of climate change, or human activities. Advances in remote-sensing technology have provided more complex features that limit the traditional approaches’ effectiveness. This work uses deep-learning-based models to enhance river extractions from satellite imagery. With Resnet-50 as the backbone network, CNN U-Net and DeepLabv3+ were utilized to perform the river segmentation of the Sentinel-1 C-Band synthetic aperture radar (SAR) imagery. The SAR data was selected due to its capability to capture surface details regardless of weather conditions, with VV+VH band polarizations being employed to improve water surface reflectivity. A total of 1080 images were utilized to train and test the models. The models’ performance was measured using the Dice coefficient. The CNN U-Net architecture achieved an accuracy of 0.94, while DeepLabv3+ attained an accuracy of 0.92. Although DeepLabv3+ showed more sta-bility during the training and performed better on wider rivers, CNN U-Net excelled at identifying narrow rivers. In conclusion, a river-segmentation model was conducted using Sentinel-1 C-Band SAR data, with CNN U-Net outperforming DeepLabv3+; this enabled detailed river mapping for irrigation- and flood-monitoring applications – particularly in cloud-prone tropical regions.
Access status: Open Access ,
Segmentacja drzewa oskrzelowego z wykorzystaniem algorytmu zamykania otworów
(Wydawnictwa AGH, 2009) Postolski, Michał; Janaszewski, Marcin Sławomir; Fabijańska, Anna; Babout, Laurent; Jędrzejczyk, Mariusz; Stefańczyk, Ludomir
Reliable segmentation of a human airway tree from volumetric computer tomography (CT) data sets is the most important step for further analysis in many clinical applications. In this paper the original airway segmentation algorithm based on discrete topology and geometry is presented. The proposed method is fully automated and takes advantage of well defined mathematical notions. Holes occur in bronchial walls due to many reasons, for example they are results of noise. Holes are common problem in previously proposed methods because in some areas they can cause the segmentation algorithms to leak into surrounding parenchyma parts of a lung. The novelty of the approach consist in the application of a dedicated hole closing algorithm which closes all disturbing holes in a bronchial tree. The experimental results showed that the method is reliable and generate good quality and accurate results.
Access status: Open Access ,
Zastosowanie kwantowych algorytmów genetycznych do selekcji cech
(Wydawnictwa AGH, 2009) Jopek, Łukasz; Nowotniak, Robert; Postolski, Michał; Babout, Laurent; Janaszewski, Marcin Sławomir
In the article a feature selection problem for k-NN classifier in image segmentation has been analyzed. Feature selection has been considered as a two criteria combinatorial optimization problem. An objective of optimization process was to find a feature subset of image points, allowing good quality of segmentation in satisfactory time. A fitness function for feature subsets has been proposed, taking into account time needed for calculation of feature values and quality of segmentation. Three population-based heuristic methods of optimization have been compared: simple genetic algorithm and its two modifications, inspired by principles of quantum computing: QiGA (Quantum-Inspired Genetic Algorithm) and GAQPR (Genetic Algorithm with Quantum Probability Representation). Results of experiments with artificial and tomography textures have been presented.
Access status: Restricted ,
Zastosowanie sekwencji wideo w celu identyfikacji samochodowych tablic rejestracyjnych
(Data obrony: 2018-08-10) Krzyżak, Paulina
Wydział Geologii, Geofizyki i Ochrony Środowiska
Celem niniejszej pracy magisterskiej jest stworzenie systemu, który na podstawie sekwencji wideo określi miejsce rejestracji przejeżdżających pojazdów. Praca opierać się będzie na zarejestrowaniu obrazu poruszających się pojazdów, analizie tej sekwencji wideo wraz z rozpoznawaniem znaków oraz określeniu miejsca rejestracji pojazdów zarejestrowanych na filmie.