Wyniki wyszukiwania - BazTech

1

Wild Image Retrieval with HAAR Features and Hybrid DBSCAN Clustering For 3D Cultural Artefact Landmarks Reconstruction

Pitchandi Perumal

Advances in Science and Technology. Research Journal

|

2022

|

Vol. 16, no 3

269--281

EN

In this digital age large amounts of information, images and videos can be found in the web repositories which accumulate this information. These repositories include personal, historic, cultural, and business event images. Image mining is a limited field in research where most techniques look at processing images instead of mining. Very limited tools are found for mining these images, specifically 3D (Three Dimensional) images. Open source image datasets are not structured making it difficult for query based retrievals. Techniques extracting visual features from these datasets result in low precision values as images lack proper descriptions or numerous samples exist for the same image or images are in 3D. This work proposes an extraction scheme for retrieving cultural artefact based on voxel descriptors. Image anomalies are eliminated with a new clustering technique and the 3D images are used for reconstructing cultural artefact objects. Corresponding cultural 3D images are grouped for a 3D reconstruction engine’s optimized performance. Spatial clustering techniques based on density like PVDBSCAN (Particle Varied Density Based Spatial Clustering of Applications with Noise) eliminate image outliers. Hence, PVDBSCAN is selected in this work for its capability to handle a variety of outliers. Clustering based on Information theory is also used in this work to identify cultural object’s image views which are then reconstructed using 3D motions. The proposed scheme is benchmarked with DBSCAN (Density-Based Spatial Clustering of Applications with Noise) to prove the proposed scheme’s efficiency. Evaluation on a dataset of about 31,000 cultural heritage images being retrieved from internet collections with many outliers indicate the robustness and cost effectiveness of the proposed method towards a reliable and just-in-time 3D reconstruction than existing state-of-the-art techniques.

2

A linearization-based hybrid approach for 3D reconstruction of objects in a single image

Kotan Muhammed, Öz Cemil, Kahraman Abdulgani

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 3

501--513

EN

The shape-from-shading (SFS) technique uses the pattern of shading in images in order to obtain 3D view information. By virtue of their ease of implementation, linearization-based SFS algorithms are frequently used in the literature. In this study, Fourier coefficients of central differences obtained from gray-level images are employed, and two basic linearization-based algorithms are combined. By using the functionally generated surfaces and 3D reconstruction datasets, the hybrid algorithm is compared with linearization-based approaches. Five different evaluation metrics are applied on recovered depth maps and the corresponding gray-level images. The results on defective sample surfaces are also included to show the effect of the algorithm on surface reconstruction. The proposed method can prevent erroneous estimates on object boundaries and produce satisfactory 3D reconstruction results in a low number of iterations.

3

The Impact of Photo Overlap, the Number of Control Points and the Method of Camera Calibration on the Accuracy of 3D Model Reconstruction

Róg Marta, Rzonca Antoni

Geomatics and Environmental Engineering

|

2021

|

Vol. 15, no. 2

67--87

EN

This research attempted to determine the optimal photo overlap, number of control points and method of camera calibration for a photogrammetric 3D model reconstruction of an object of cultural heritage value. Terrestrial images of the object were taken with a hand held digital camera and processed in the ContextCapture software using the Structure from Motion (SfM) algorithm. A total station was used to measure ground control points (GCPs) and check points. Here, the research workflow, methodology, and various analyses concerning different configurations of the aforementioned factors are described. An at tempt to assess the parameters which should be implemented in order to pro vide a high degree of accuracy of the model and reduce time consumption both during fieldwork and data processing was taken. The manuscript discusses the results of the analyses and compares them with other studies presented by different authors and indicates further potential directions of studies within this scope. Based on the authors’ experience with this research, some general conclusions and remarks concerning the planning of photo acquisition from the terrestrial level for the purpose of 3D model reconstruction were formulated.

4

The measurements of surface defect area with an RGB-D camera for a BIM-backed bridge inspection

Wójcik Bartosz, Żarski Mateusz

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e137123

EN

Bridge inspections are a vital part of bridge maintenance and the main information source for Bridge Management Systems is used in decision-making regarding repairs. Without a doubt, both can benefit from the implementation of the Building Information Modelling philosophy. To fully harness the BIM potential in this area, we have to develop tools that will provide inspection accurate information easily and fast. In this paper, we present an example of how such a tool can utilise tablets coupled with the latest generation RGB-D cameras for data acquisition; how these data can be processed to extract the defect surface area and create a 3D representation, and finally embed this information into the BIM model. Additionally, the study of depth sensor accuracy is presented along with surface area accuracy tests and an exemplary inspection of a bridge pillar column.

5

Asesment of state-of-the-art methods for bridge inspection: case study

Wójcik B., Żarski M.

Archives of Civil Engineering

|

2020

|

Vol. 66, nr 4

343--362

EN

Despite the progress in digitization of civil engineering, the process of bridge inspection is still outdated. In most cases, its documentation consists of notes, sketches and photos. This results in significant data loss during structure maintenance and can even lead to critical failures. As a solution to this problem, many researchers see the use of modern technologies that are gaining popularity in civil engineering. Namely Building Information Modelling (BIM), 3D reconstruction and Artificial Intelligence (AI). However, despite their work, no particular solution was implemented. In this article, we evaluated the applicability of state-of-the-art methods based on a case study. We have considered each step starting from data acquisition and ending on BIM model enrichment. Additionally, the comparison of deep learning crack semantic segmentation algorithm with human inspector was performed. Authors believe that this kind of work is crucial for further advancements in the field of bridge maintenance.

PL

Pomimo postępu w cyfryzacji budownictwa, proces inspekcji mostów jest nadal przestarzały. W większości przypadków jego dokumentacja składa się z notatek, szkiców i zdjęć. Powoduje to znaczną utratę danych podczas fazy utrzymania konstrukcji, a nawet może prowadzić do awarii. Wielu badaczy jako rozwiązanie tego problemu upatruje w wykorzystaniu nowoczesnych technologii, które zyskują na popularności w inżynierii lądowej. Technologii takich jak modelowanie informacji o budynku (BIM), rekonstrukcja 3D i sztuczna inteligencja (AI). Jednak pomimo wykonanej do tej pory pracy nie zaimplementowano żadnego konkretnego rozwiązania. W tym artykule oceniliśmy przydatność tych najnowocześniejszych metod na podstawie studium przypadku. Rozważaliśmy każdy krok począwszy od pozyskania danych, a skończywszy na wzbogaceniu modelu BIM. Ponadto przeprowadzono porównanie algorytmu segmentacji semantycznej pęknięć w uczeniu głębokim z ludzkim inspektorem. Uważamy, że tego rodzaju prace są kluczowe dla dalszych postępów w utrzymaniu mostów.

6

A stereovision system for three-dimensional measurements of machines

Grudziński Marek, Marchewka Łukasz

Zeszyty Naukowe Akademii Morskiej w Szczecinie

|

2019

|

nr 58 (130)

16--23

EN

The modern manufacturing or transportation machines that are used in industrial processes require continuous supervision in certain circumstances and even manual control by a human. Despite the fact the machines are more and more reliable and accurate than they used to be there is still the need for manual and time-consuming programming and safety control, especially when the external conditions change. For the operation of large machines, where the risk of damage and even disaster exists, an additional supervisory system based on vision devices could be utilized. The vision systems are commonly used in a range of simple 2D detection as well as very precise 3D reconstruction. The stereovision systems could be applied for unusual operations, especially in terms of safety and collision avoidance, such as crane observations while transporting a heavy load, robot and CNC machine preparation and normal operation. Through the use of optical devices the observed objects could be quickly positioned. In this research a test bench for stereovision reconstruction for the example of a robotic arm has been presented. The calibration procedures have been explained and accuracy tests in a large measuring volume were performed. Finally the possibilities of the applications and the utilization of such a system have been assessed.

7

The effect of patterns on image-based modelling of texture-less objects

Hafeez J., Jeon H.-J., Hamacher A., Kwon S.-C., Lee S.-H.

Metrology and Measurement Systems

|

2018

|

Vol. 25, nr 4

755--767

EN

The task of generating fast and accurate three-dimensional (3D) models of objects or scenes through a sequence of non-calibrated images is an active field of research. The recent development in algorithm optimization has resulted in many automatic solutions that can provide an accurate 3D model from texture-full objects. Structure-from-motion (SfM) is an image-based method that uses discriminative point-based feature identifier, such as SIFT, to locate feature points in the images. This method faces difficulties when presented with the objects made of homogenous or texture-less surfaces. To reconstruct such surfaces a well-known technique is to apply an artificial variety by covering the surface with a random texture pattern prior to the image capturing process. In this work, we designed three series of image patterns which are tested based on the contrast and density ratio which increases from the first to the last pattern within the same series. The performance of the patterns is evaluated by reconstructing the surface of a texture-less object and comparing it with the true data. Using the best-found patterns from the experiments, a 3D model of a Moai statue is reconstructed. The experimental results demonstrate that the density and structure of a pattern highly affects the quality of the reconstruction.

8

Robust two-view reconstruction procedure for geometrical model retrieving

Walczak J., Wojciechowski A.

Journal of Applied Computer Science

|

2018

|

Vol. 26, nr 1

87--104

EN

In this paper we present the enhancement of the standard two-view reconstruction procedure. An ordinary approach assumes determination of points’ correspondences followed by projection matrix estimation, to finally refine results with bundle adjustment taking as a cost function reprojection error. Our contribution is realized in two manners: introducing an additional step of outliers rejection, changing cost function of bundle adjustment process to Relative Reprojection Error (R) and applying central difference as a method for Jacobian matrix approximation. Tests revealed gain in average R with lower variance, for confidence level of 0.95. Besides accuracy improvement, the suggested modifications supply the final result in the time virtually independent on initial object’s complexity and, in most cases, shorter than the standard approach.

9

Applications of modern imaging technology in orthopaedic trauma surgery

Krakowski Przemysław, Karpiński Robert, Maciejewski Marcin

Applied Computer Science

|

2018

|

Vol. 14, no 3

96--106

EN

Orthopaedic trauma surgery is a complex surgical speciality in which anatomy, physiology and physics are mixed. Proper diagnosing and based on that planning and performing surgery is of crucial matter. This article briefly summarizes available radiological modalities used for diagnostics and for surgical planning. It focuses on utility of rapid prototyping process in trauma surgery. Moreover, a case study in which this technique was used is described. Rapid prototyping proved its usefulness and in future it may become a modality of choice for planning complex trauma procedures.

10

Damage evaluation in composite structures based on image processing of ultrasonic c-scans

Wronkowicz A., Katunin A.

Studia Informatica

|

2017

|

Vol. 38, nr 1B

31--40

EN

The article presents a method of reconstruction of planar ultrasonic maps into a three-dimensional form based on levels of attenuation of ultrasonic waves through a tested composite structure. A developed algorithm is based on image processing techniques, which allows enhancing ability of interpretation of damage extent at particular depths of a tested structure.

PL

Artykuł przedstawia metodę rekonstrukcji płaskich map ultradźwiękowych do postaci trójwymiarowej na podstawie poziomów tłumienia fal ultradźwiękowych przez badaną strukturę kompozytową. Opracowany algorytm został oparty na technikach przetwarzania obrazu, które pozwalają na wspomaganie interpretacji rozległości uszkodzeń na poszczególnych poziomach głębokości w badanej strukturze.

11

Analysis of 3D photogrammetric reconstruction

Velichova D.

Journal Biuletyn of Polish Society for Geometry and Engineering Graphics

|

2017

|

Vol. 30

59--62

EN

Paper brings information about process of analytics reconstruction of 3D real data of objects selected from photographic images using software application CamWitt. Reconstruction algorithms are based on classical methods of photogrammetry and principles of epipolar geometry.

PL

W pracy podano analityczną metodę odtwarzania rzeczywistych danych 3D obiektów wybranych z obrazów fotograficznych za pomocą aplikacji CamWitt. Algorytmy rekonstrukcji oparte są na klasycznych metodach fotogrametrii i zasadach geometrii epipolarnej.

12

Multibeam data processing for 3D object shape reconstruction

Kulawiak M., Łubniewski Z.

Hydroacoustics

|

2017

|

Vol. 20

105--112

EN

The technology of hydroacoustic scanning offers an efficient and widely-used source of geospatial information regarding underwater environments, providing measurement data which usually have the structure of irregular groups of points known as point clouds. Since this data model has known disadvantages, a different form of representation based on representing surfaces with simple geometric structures, such as edges and facets, is preferred for data featuring seabed surface relief and various underwater objects. In this paper, the authors propose a multiple-step approach to three-dimensional surface reconstruction from multibeam sonar measurements, relying on the proper application of various algorithms for noise reduction, data rasterization and classification. The results obtained by combining several different surface reconstruction algorithms with the proposed data processing technique were tested, and the strengths and weaknesses of each method were highlighted.

13

Digital Material Representation Model of Porous Microstructure Based on 3D Reconstruction Algorithm

Madej Ł., Mojżeszko M., Chrapoński J., Roskosz S., Cwajna J.

Archives of Metallurgy and Materials

|

2017

|

Vol. 62, iss. 2A

563--569

EN

Development of the Digital Material Representation (DMR) model, based on 3D reconstruction algorithm and serial sectioning, is the main goal of the present paper. Details on the serial sectioning and image processing algorithms are presented first. Serial sectioning is realized on the basis of light microscopy (LM). Then concept of 3D reconstruction and developed algorithms are presented. Two approaches, based on shape coefficients and the flood fill algorithms, are developed to identify corresponding features on subsequent 2D images. Then, the interpolation algorithm to reconstruct 3D volume between 2D images is presented. Finally, obtained 3D model is an input for finite element mesh generation software for subsequent finite element calculations.

14

An approach to computer-aided reconstruction of museum exhibits

Kęsik J., Montusiewicz J., Kayumov R

Advances in Science and Technology. Research Journal

|

2017

|

Vol. 11, no 2

87--94

EN

The article discusses the possibility of using 3D laser and 3D structured light scanning technology to support the restoration of museum objects and presents the concept of applying techniques of 3D scanning and CAD processing to create a model of the missing fragment of a museum object, based on scans of the damaged surface and fragments of the object with a similar shape. The resulting model can be used as a base element in the restoration of the original shape of the artifact, both virtually and in reality. The paper also presents the proposal of a process of reconstructing a missing fragment model of an actual museum object (an exhibit from the Zamoyski Museum in Kozłówka) using the method in question and mobile 3D scanning equipment.

15

Numerical prediction of the effect of aortic Left Ventricular Assist Device outflow-graft anastomosis location

Mazzitelli R., Boyle F., Murphy E., Renzulli A., Fragomeni G.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 2

327--343

EN

A Left Ventricular Assist Device (LVAD) is used to provide haemodynamic support to patients with critical cardiac failure. As LVADs generate continuous flow to better understand the haemodynamic effects of these devices under different working conditions, and particularly in relation to possible outflow-graft anastomosis location, we performed 3D one-way-coupled fluid–structure-interaction (FSI) for three different LVAD working conditions and with the anastomosis location in the ascending aorta and in the descending aorta. The anatomical model used in this study is a patient-specific geometry reconstructed from computed tomography images and the mechanical support considered is similar to the Jarvik 2000®Heart LVAD. Endothelial cells can be influenced by wall stress generated from the blood flow in the artery, so they can produce vascular complications. For this reason, the second aim of this study is to evaluate and analyse, using different mechanical indicators, the wall shear distribution upon the luminal surface of the aorta generated by an LVAD. These numerical investigations demonstrate the utility of one-way-coupled FSI models to compare the haemodynamic conditions for the two LVAD outflow-grafts anastomosis locations and how both affect the aorta and its wall stress. Furthermore, the mechanical indicators allow the identification of wall regions at greater risk of atherosclerosis. The results of this study indicate that an LVAD outflow-graft anastomosis location in the ascending aorta is the optimal configuration.

16

Uwagi na temat predynastycznej architektury z suszonej cegły mułowej w Egipcie. Metodyka dokumentacji i próba rekonstrukcji

Karmowski J.

Wiadomości Konserwatorskie

|

2014

|

Nr 39

45--53

PL

Niniejszy artykuł traktuje o problematyce dokumentacji i rekonstrukcji predynastycznej architektury z suszonej cegły mułowej na terenie Egiptu. Opisano w nim metody pozyskiwania danych oraz proces wykorzystania ich do celów rekonstrukcji dawnej zabudowy osadniczej. Zaprezentowano tak że proces powstawania oraz końcowe efekty trójwymiarowej rekonstrukcji opisywanej zabudowy opartej na tradycyjnej dokumentacji archeologicznej połączonej z danymi pozyskanymi za pomocą tachimetru. W artykule poświęcono również miejsce na refleksję na temat suszonej cegły mułowej. Opisano współczesny proces produkcji tego materiału budowlanego, jego właściwości oraz sugestie na temat sposobu dokumentacji jego pradziejowych odpowiedników odkrywanych podczas archeologicznych badań wykopaliskowych.

EN

This paper examines methodological descriptions of obtaining and applying data to reconstruct mud-brick PreDynastic architecture from Ancient Egypt. These methods include the creating a three dimensional virtual reconstruction based on traditional archaeological documentation and geodesic measurements. I also provide information about mud-bricks as a building component including the modern process of mud-brick production, its characteristics as a building material and suggestions for documentation methods of archaeological examples.

17

A Survey of Passive 3D Reconstruction Methods on the Basis of More than One Image

Siudak M., Rokita P.

Machine Graphics and Vision

|

2014

|

Vol. 23, No. 3/4

57--117

EN

The research on the 3D scene reconstruction on the basis of its images and video recordings has been in progress for many years. As a result there is a number of methods concerning how to manage the reconstruction problem. This article's goal is to present the most important methods of reconstruction including stereo vision, shape from motion, shape from defocus, shape form silhouettes. shape from photo-consistency. All the algorithms explained in this article can be used on images taken with casual cameras in an ordinary illuminated scene (passive methods).

18

Wykorzystanie pomiarów mikroskopowych 3D do rekonstrukcji pęknięć powstających w procesach kształtowania blach

Morawski Ł., Jasiński C., Kocańda A.

Prace Naukowe Politechniki Warszawskiej. Mechanika

|

2013

|

z. 253

39--44

PL

W referacie przedstawiono metodę rekonstrukcji defektów 3D, wykorzystującą zjawisko głębi ostrości w układach optycznych mikroskopów. Przedstawiono stanowisko oparte na działaniu mikroskopu cyfrowego, a także algorytm uzyskiwania trójwymiarowych obrazów. Wykorzystując opisane stanowisko wykonano pomiary geometrii 3D wad powstałych w procesach gięcia i wytłaczania.

EN

The paper presents a method of 3D reconstruction of defects, using the phenomenon of low depth of field in the microscope system. The components of the measurement system based on a digital microscope, and the algoritm for obtaining three-dimensional images were discussed. Next, the examples of 3D defect reconstruction were presented for bending and stretching processes.

19

3D Structure of Positive Corona Streamer Reconstruction Using Stereo Photography and Computer Algorithm

Kocik M., Tański M., Mizeraczyk J., Dembski J.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 10b

153-155

EN

3D structure of corona streamer was measured using stereo photography method. To enhance and speed-up the image processing computer algorithms were developed for automatic reconstruction of 3D structure of streamers.

PL

W niniejszym artykule przedstawiono metodę rekonstrukcji struktury przestrzennej strimera wyładowania koronowego. Dzięki zastosowaniu opracowanych algorytmów komputerowych możliwe było zautomatyzowanie procesu odtwarzania struktury strimera z wykonanych metodą stereofotografii obrazów.

20

Wykorzystanie otwartego oprogramowania do rekonstrukcji stanowisk pracy

Grabowski A.

Pomiary Automatyka Robotyka

|

2012

|

R. 16, nr 2

183-188

PL

Systemy wizyjne są od wielu lat stosowane do rekonstrukcji 3D rzeczywistych obiektów różnego typu. Zwykle jednak ich zastosowanie wiąże się z pewnymi ograniczeniami, dotyczącymi m.in. rozmiaru skanowanych obiektów lub warunków oświetlenia. W artykule przedstawiono uniwersalną, a zarazem niewymagającą dużych nakładów finansowych, metodę rekonstrukcji stanowisk pracy opartą na oprogramowaniu o otwartym źródle takim jak OpenCV i PCL (Points Cloud Library). Opracowana metoda daje dużą dokładność rekonstrukcji, może być wykorzystana zarówno do małych jak i dużych obiektów oraz jest w dużej mierze niezależna od zewnętrznego oświetlenia - działa w zamkniętych pomieszczeniach oraz na zewnątrz. Podstawowym celem przedstawionej metody jest rekonstrukcja 3D stanowisk pracy w celu testowania wizyjnych systemów bezpieczeństwa z wykorzystaniem technik rzeczywistości mieszanej.

EN

Vision systems are used for many years to reconstruct the 3D objects of various types. Usually, however, their use is associated with certain limitations, e.g. size of the scanned object or lighting conditions. This paper presents a universal and lowcost method of 3D reconstruction of work places based on open source software such as OpenCV and PCL (Points Cloud Library). The developed method gives high accuracy of reconstruction, can be used for both small and large objects, and is largely independent of ambient light - works indoors and outdoors. Presented method will be used for 3D reconstruction of the work places in order to test the video based safety systems with the help of mixed reality techniques.