|
Accepted papers
Spectral evaluation of the vital state of Quercus robur L. under simulated drought conditions
P.A. Zybinskaya, A.V. Tretyakova, P.A. Krylov
Accepted: 2024-07-24
Abstract
Non-destructive spectral methods of analysis are increasingly being used to study the content of plant metabolites, evaluate morpho-physiological and biochemical indicators, as well as evaluation of the vital state. Visualization of the vital state through spectral profiles can provide a more detailed picture of plant adaptation to stress. To model experimental drought, 5-6 month-old Quercus robur L. seedlings were divided into three groups: control and experimental groups with and without watering (drought), with 15 seedlings in each group. Spectral evaluation of leaf blades was performed using a portable spectroradiometer SpectraPen SP110 Uvis and a plant analyzer Dualex Scientific+ at 0 (control), 168 (one week), and 336 (two weeks) hours. As a result of spectral analysis, spectrograms of radiation absorption of Q. robur leaf blades were obtained, as well as the content of the sum of chlorophylls, flavonols and anthocyanins under watering and drought conditions. The study revealed changes in the spectrograms of absorption of Q. robur leaves related to the content of metabolites. The difference in absorption peaks between the groups became more expressed over time under the influence of drought. The pigment content in the leaf blades varied during the experiment, which indicates plant adaptation to stress. Preliminary results of the study can be used to expand knowledge about ways to evaluate the vital state of woody plants in the field.
Calculation of a parallaxpanoramogram in autostereoscopic systems with inconsistent monitor and lens raster parameters
N.V. Kondratiev, Yu.N. Ovechkis, A.I. Vinokur, D.A. Arsentiev
Accepted: 2024-07-11
Abstract
A significant disadvantage of the multi-point of view autostereoscopic method is a drop in image resolution with an increase in the number of points of view. An effective means of increasing the resolution is the use of an inclined lens raster and vertical encoding the colors of the point of view. Algorithmically simple coding is obtained at optimal tilt angles, the tangent of which is 1 divided by a multiple of 3 (1/3, 1/6, etc.). This requirement imposes significant restrictions on the coordination of the geometric parameters of the equipment – the display panel and the lens raster. The approaches to spatial color coding proposed in this article and the algorithms implementing them make it possible to significantly expand the possibilities of creating autostereoscopic displays. The experimental work carried out convincingly confirms the theoretical conclusions. The main practical result was the developed software that allows fine-tuning of the angle of inclination of the raster and calculating a multi-point of view parallaxpanoramogram for a specific set of equipment.
Application of the cognitive load indicator of a graphic element to justify the requirements for a long-range discrimination radar visualization system
S.V. Matseevich, U.A. Vladko, A.D. Zyuzina, M.N. Mochalov, A.S. Zakharov
Accepted: 2024-06-15
Abstract
The article presents the results of a study on the use of an indicator of cognitive load on the operator of a long-range discrimination (LRD) radar when interacting with the graphic element of the visualization system of the LRD radar under the influence of destructive factors.
An original method for substantiating the requirements for the structure of a visualization system is proposed, based on combining the principles of the theory of engineering psychology, ergonomics, cognitive graphics, taking into account the cognitive resources of the radar operator.
The technique is formalized in the form of a problem of minimizing a general criterion characterizing the efficiency of operators and their capacity for information in the “man-machine” system, taking into account the cognitive load indicator.
It is shown that the use of the indicator makes it possible to justify the requirements for the structure of the visualization system, namely a graphical interface that can reduce the influence of negative factors on the operator of the radar station, especially under strict time constraints.
The results of a computational experiment to evaluate the effectiveness of using the cognitive load indicator when choosing a graphic element of a visualization system are presented, demonstrating an increase in the functional characteristics of the radar operator when performing tasks.
Visualization functions in argumentation representation software
D.E. Prokudin, E.N. Lisanyuk, I.R. Baymuratov
Accepted: 2024-06-09
Abstract
In the historical development of argumentation as a scientific direction and applied field, a number of ways of its visual representation have been developed. In the middle of the 20th century, within the framework of the theory of argumentation, in addition to the logical, rhetorical and computational concepts used since ancient times, new concepts were formulated that shaped the basis for the representation of argumentation using software. First of all, this foundation was laid by researchers who put forward new approaches to its formalization (Stephen Toulmin, Phan Mihn Dung). Since the beginning of the 21st century, the dynamics of informatization of scientific activity and education have led to the development of software designed to represent argumentation and evidence-based reasoning. Both textual and graphical tools are used in the software to visually represent argumentation for solving various tasks depending on the purpose of using the software. We examine the possibilities of the existing software for visualization of argumentation and identify its features and main functions, which open a possibility for a more justified and goal-oriented selection of appropriate tools for the effective solution of various tasks. The article is based on the results of a talk and discussion at the All-Russian scientific conference "Scientific service on the Internet" in 2023.
Visualization of hybrid virtual scenes using hardware-accelerated ray tracing and rasterization
P.Yu. Timokhin, M.V. Mikhaylyuk
Accepted: 2024-06-09
Abstract
This paper discusses the task of real-time visualization of hybrid virtual scenes that combine traditional polygonal scenes and procedural objects. An approach to solve this task on modern multicore graphics processors is proposed, in which the visualization of the polygonal scene is performed via rasterization and non-polygonal procedural objects - using hardware-accelerated ray tracing. The paper describes developed methods and algorithms allowing two such synthesized images to be merged by depth using the bundle of programming interfaces Vulkan-OpenGL. Based on the proposed methods and algorithms, software complex prototype, implementing real-time visualization of hybrid scenes, was created. The complex was tested on a number of scenes with complicated procedural objects specified by 3D scalar fields (point clouds). The results of the approbation confirmed the feasibility of obtained solutions and their applicability to virtual environment systems, scientific visualization, virtual laboratories, video simulators, educational applications, etc.
Modeling and visualization of sedimentation in a viscous incompressible fluid
V. A. Galkin , A.O. Dubovik, A.D. Smorodinov
Accepted: 2024-06-09
Abstract
The article considers the equation of hydrodynamics with a sliding condition at the boundary and the motion of an inertialess non-diffusing impurity in a viscous incompressible liquid in a cylindrical region. Diffusion processes in dispersed systems are investigated – the effect of parachuting a falling large particle in a liquid-filled medium. The result of a numerical and analytical solution of a system of equations consisting of the Navier-Stokes equation for an incompressible fluid and the convection-diffusion equation is presented. It is shown that in order to calculate the trajectory of an impurity particle, it is necessary to solve the Cauchy problem in three-dimensional space with given initial conditions for each impurity particle. A series of computational experiments has been carried out to simulate the dynamics of a heavy impurity in an incompressible liquid. The initial conditions for the Cauchy problem are set based on a black-and-white image, where a black pixel is considered an impurity particle. The developed software has been tested to determine the degree of confidence in the calculations performed by solving the initial problem in reverse order, for which the initial conditions for the Cauchy problem were chosen equal to the value at the last step of the initial problem. A visual and quantitative analysis of the results obtained is presented based on the developed software package using the MathGL library for the C++ programming language.
Use of 3d Modelling and Printing Capabilities in Students' Project Activities in the Study of Comparative Anatomy of Animals
T.Yu Kolpakova
Accepted: 2024-06-08
Abstract
The article discusses the possibilities of using 3D technologies in biological laboratories of the Technopark of universal pedagogical competencies of Omsk State Pedagogical University when training future bioecologists and biology teachers. The features and potential of using new methods in training students - biologists and future teachers - are revealed. The authors present the results of using new equipment in teaching comparative animal anatomy in a pedagogical university. The article discusses the possibilities of development and creation of a training 3D model, features of printing on a 3D printer and subsequent refinement of the model of different types of animal vertebrae, which allows you to clearly demonstrate the features of their morphology and spatial arrangement, which increases the efficiency and quality of education of students. It is shown that the use of modern 3D technologies provides a certain advantage by adapting the educational process to the modern requirements of the digital educational environment, increasing the visibility of anatomical objects, which increases the efficiency and quality of students’ learning. Project activity of students involves an independent creation of three-dimensional anatomical models of different types of animal vertebrae, which contributes to the development of a creative approach in acquiring knowledge and skills. Such creative work creates a good emotional atmosphere, increases motivation for learning and the level of self-esteem, and significantly complements the process of studying comparative animal anatomy.
Comparison of the Effectiveness of Using Various Approaches in Detecting Objects on Low-Quality Images
A. Provorova, I. Polyakova, E. Kuzmicheva
Accepted: 2024-06-05
Abstract
Machine methods of image analysis are gaining popularity in various fields of life. However, the question remains as to how effective such algorithms are on low-quality data, such as those that can be used in the field of telemedicine. The work provides a comparative analysis of various approaches to object detection in MRI brain images taken from a computer screen. For the recognition of brain contours in the image, a classical morphometric approach (OpenCV library), the Viola-Jones algorithm, and two deep learning algorithms, YOLOv8 and EfficientDet, were used. The comparison of these methods was conducted in terms of the quality of object detection in the image. To assess the quality, we used the IoU metric, as well as measured the amount of memory used and the speed of algorithm execution. As a result of the comparison, we found that the YOLOv8 model demonstrated the best performance in terms of object detection quality. However, its performance was unstable in cases of low-quality images with high levels of noise. Among the considered approaches, YOLOv8 is also the most memory-intensive. The YOLOv8 network architecture can be considered the best candidate for further practical application in terms of average performance and resistance to noise.
On visualization in wave structure control using distributed heat sources
A.K. Alekseev, A.E. Bondarev
Accepted: 2024-06-05
Abstract
Flow control by spatially distributed stationary heat sources is considered for the two-dimensional Euler equations. The initial flow, characterized by the interaction of Edney-type compaction jumps, was modified with the help of heat sources so as to reduce the maximum pressure on the body surface. The problem was solved in an optimization formulation using coupled equations to calculate the gradient of the target functional. In addition to visualization of flow parameters in this problem, visualization of the distribution of conjugate parameters and heat sources is of interest.
Visually salient region detection in omnidirectional images using wavelet textural feature map
Manisha Mane, Anand Bhaskar
Accepted: 2024-06-04
Abstract
Salient object detection is a crucial aspect of computer vision that involves identifying the most prominent area in a 2D image. However, predicting salient regions in omnidirectional images can be challenging due to their circular field of view.To facilitate saliency detection, pre and post-processing are required, which involves converting the image into an equirectangular projection (ERP). In this study, we propose a detailed approach to saliency detection for omnidirectional images using the wavelet domain. Our proposed model utilizes a 2-D wavelet transform to decompose and reconstruct images in the CIELAB space.The texture channel map is then calculated, followed by the feature map, where salient regions are marked using Gaussian filtering and entropy. Our experimental results demonstrate that this method is highly effective for detecting salient objects in omnidirectional images.
On the visualization of subattractor under mixed tidal forcing
Stepan Elistratov, Ivan But
Accepted: 2024-05-18
Abstract
One of the principle conditions of a wave attractor appearance is a periodic external forcing. Real forcing in natural basins caused by tidal interaction is more complex than a monochromatic which is usually used in internal wave attractors investigations. Multi-frequency forcing may lead to the multiple wave attractor formation, some of them may be of low energy, which affects their detection. In the article we simulate a mixed forcing for an internal wave attractor flow and visualize subattractor formed due to this forcing type using several methods, including Proper Orthogonal Decomposition. It is shown that the latter method reveals sub-attractor even in case of highly turbulent flow.
Visualization of turbulent wakes behind large particles
A.A. Mochalov, A.Yu. Varaksin
Accepted: 2024-05-17
Abstract
An attempt was made to visualize the flow formed in the wake of large particles moving in a downward turbulent airflow in the channel. The paper also considers the possibilities of reconstructing velocity fields behind a large particle from visual data. A diagram of the experimental setup is shown (geometry of the working area, auxiliary and main equipment). The PIV (Particle Image Velocimetry) system is briefly described. A technique for visualizing multiphase flow “gas – solid particles” is proposed. The original images of large particles (spheres) are shown. The results of the experimental determination of the characteristics of the wake vortex behind the rear critical point of a large particle are presented.
Modeling the solution of an ordinary differential equationby the Functional voxel method
A.V. Tolok, N.B. Tolok
Accepted: 2024-05-17
Abstract
This work discusses an approach to modeling an ordinary differential equation by the Functional Voxel method (FV method). The proposed approach is an automated development of the isocline method and is based on the principles of differentiation and integration developed for FV modeling. The isocline method is analyzed as a mean of constructing a tangential field for solving the first and second order ordinary differential equation. The selected examples demonstrate the principle of constructing a FV model as a basis for obtaining integral curves. An algorithm for obtaining an integral curve of a differential equation by the means of the Functional Voxel modeling is described. A visual and numerical comparative analysis of the obtained results of the FV modeling with known examples is carried out. Unlike the isocline method, where the result is a graphical construction of constant tangent lines, in the case of a Functional voxel model we get a graphical representation of the area of local functions at each point of the integral curve corresponding to the solution of the problem.
Visualization of the structure of vapor-liquid flow during subcooled R113 refrigerant boiling under preburnout conditions
N.V. Vasil’ev, S.N. Vavilov, Yu.A. Zeigarnik, E.A. Lidzhiev
Accepted: 2024-05-06
Abstract
Boiling of dielectric liquids subcooled to the saturation temperature is a promising method for cooling modern electronic devices. This method makes it possible to remove sufficient heat flux densities (q), maintain the temperature of chip interfaces at the required level, and not create undesirable conditions leading to electrical breakdown in the event of a leak in the coolant circuit. The safe use of the boiling process of subcooled liquid is limited by heat flow densities, at which large agglomerates of the vapor phase appear in the core of the coolant flow, which carries the risk of hydraulic expansion of the applied cooling systems from parallel channels.
In this work, using visualization through high-speed video recording (with a frequency of 5–10 kHz), an experimental study of the evolution of the structure of a two-phase flow during boiling of subcooled dielectric liquid R113 under preburnout conditions was carried out. It has been shown that, also characteristic of water, at q close to critical, the formation of large vapor agglomerates in the R113 flow. It has been established that an increase in the degree of subcooling and mass velocity leads to an increase in q at the moment vapor agglomerates appear. The influence of the heating rate of the heat-transfer plate on the structure of the two-phase flow in preburnout conditions and on the value of q at the moment of burnout is shown.
Application of Modern Object Tracking Technologies to the Task of Aortography Key Point Detection in Transcatheter Aortic Valve Implantation
V.V. Laptev, N.A. Kochergin
Accepted: 2024-04-21
Abstract
Object detection, as one of the most fundamental and challenging problems in computer vision, has attracted much attention in recent years. Over the past two decades, we have witnessed the rapid technological evolution of object detection and its profound impact on the whole field of computer vision. In this paper, aortography key point detection approaches for transcatheter aortic valve implantation based on machine learning tools are discussed. The paper provides a description and analytical comparison of such popular methods as "object detection", "pose estimation". As a result of this study, a visual assessment system is proposed to facilitate the performance of the intervention procedure. The final accuracy of the proposed system reaches 79.3% with an analysis speed of 12 ms per image.
Многоканальная регистрация ЭКГ с поверхности женского торса и визуализация характеристик сердца
Ю.С. Данилкина, М.Н. Крамм, Т.Л.Н. Чыонг, А.Ю. Бодин, Д.В. Краюшкин
Accepted: 2024-04-17
Abstract
Работа посвящена разработке электрокардиографического жилета, учитывающего особенности женского торса и предназначенного для записи электрокардиосигналов (ЭКС) множественных униполярных отведений. Главной задачей обработки таких ЭКС является визуализация карт распределения электрических потенциалов на поверхности торса и поверхности эпикарда. Особенностью подобного подхода является использование достаточно большого количества электродов на поверхности торса (45-80) и решение обратной задачи для перехода от потенциалов на поверхности торса к потенциалам на поверхности эпикарда Основные сложности реализации этого подхода – это установка достаточно большого числа электродов и сопутствующие существенные временные затраты. Разработка системы регистрации ЭКС на основе электрокардиографического жилета с предустановленными электродами, позволяет оперативно осуществлять установку электродов, запись ЭКС и будет способствовать повышению качества диагностики заболеваний сердечно сосудистой системы. В данной работе показана разработка электрокардиографической системы с 46 электродами, позволяющей оперативно осуществлять запись ЭКС, а также проведены испытания. Данное изделие способствует повышению качества диагностики заболеваний сердечно-сосудистой системы.
Integration of Physical Reality Objects with Their 3D Models Visualized in Virtual Environment Systems
A.V. Maltsev
Accepted: 2024-04-12
Abstract
The paper describes methods and approaches for integrating, from the user's point of view, three-dimensional virtual models visible to them in a virtual reality headset, and their physical prototypes. This allows for the addition of some important elements of physical reality to the virtual environment, such as tactile and muscle-motor sensations. Developed solutions are based on the use of wireless HTC Vive trackers, which determine their position and orientation in space and have the ability to be attached to various objects in the real world. An original approach to building a tracking system from several controllers of such type with one anchor element selection is proposed, as well as new methods for real-time integration of physical reality objects with their virtual models by means of functional control schemes with blocks for the Vive trackers. Software modules were created based on developed methods and approaches. Approbation of them was carried out in virtual environment system VirSim and showed adequacy and effectiveness of proposed solutions when using in virtual environment systems and training complexes.
Visualization and Classification of Human Movements Based on Skeletal Structure: A Neural Network Approach to Sport Exercise Analysis and Comparison of Methodologies
V.O. Kuzevanov, D. V. Tikhomirova
Accepted: 2024-03-27
Abstract
The authors of the paper review and compare different existing approaches to Human Action Recognition (HAR), analyze the advantages and disadvantages of platforms for extracting human skeletal structure from video stream, and evaluate the importance of visual representation in the motion analysis process. This paper presents an example implementation of one of the approaches to HAR based on the use of interpretability and visual expressiveness inherent in skeletal structures. In this work, an ad hoc network with Long Short-Term Memory (LSTM) for human activity classification is designed and implemented, which has been trained and tested in the domain of sports exercises. LSTM incorporation of memory cells and gating mechanisms not only mitigates the vanishing gradient problem but also enables LSTMs to selectively retain and utilize relevant information over extended sequences, making them highly effective in tasks with complex temporal dependencies. The problem with a fading gradient is quite common in deep neural networks and is that if the error is back propagated during the training of the network, the gradient can decrease strongly as it travels through the layers of the network to the initial layers. This can lead to the fact that the weights in the initial layers are practically not updated, which makes training of these layers impossible or slows down its process. The resulting solution can be used to create a real-time virtual fitness assistant. The resulting solution can be used to create a real-time virtual fitness assistant. In addition, this approach will make it possible to create interactive training applications with visualization of human skeletal structure, motion analysis and monitoring systems in the field of medicine and rehabilitation, as well as for the development of security systems with access control based on the analysis of visual data on the movement of human body parts.
Interactive Geoinformation System for Dynamic Visualization of Auroral Oval Characteristics Based on Component-Oriented Programming Patterns
A.V. Vorobev, G.R. Vorobeva
Accepted: 2024-03-27
Abstract
The practical need for operational monitoring of the position dynamics of the auroral oval is due to the negative technospheric manifestations of space weather effects observed in this spatial region. However, the well-known software tools for modeling the auroral oval solve this problem inefficiently from the point of view of informativeness and ergonomics. The paper proposes an approach to dynamic visualization of the characteristics of the auroral oval, which is available at the program level in the form of a traditional web application with the ability to render visual elements in the browser, as well as in the format of a standalone service like RESTful-API. The developed solution provides visualization of the following parameters: the probability of observing the glow of the upper layers of the atmosphere with the naked eye, the electric and magnetic potentials of the field in the region of the northern auroral belt, as well as various types of auroral precipitation. It is assumed that the proposed approach will make it possible to significantly increase the efficiency of the study of parameters in the auroral oval region by specialists and scientists in the relevant fields. At the same time, the high internal and low external connectivity of the developed software modules allow them to be integrated into third-party applications of various profiles and purposes.
BBMS: Investigation to Single Colour Image Visibility Improvement in Turbid Media through Biorthogonal Wavelet Based Depth-map Estimation
Sangita Roy
Accepted: 2024-03-20
Abstract
Electronic imaging needs good quality, high resolution (HR) digital images for highlighting finer details of the image. Normally images captured by ordinary digital camera are post pro cessed with available software instead of high cost CMOS sensor phased camera. Problem commonly faced with these images may get degraded due to the scattering media which deteriorates contrast, shifts colour, and make overall image whitish. Information from the distant objects suffer from poor medium transmission as well as noise amplification. Biorthogonal wavelet denoising (BWD), compress sparsely in frequency -time space, removes noise from depth estimation and makes the transmission smooth. Moreover, single image recovery is a serious challenge and ill posed problem. The recovered image improves compare to degraded image significantly and dis cards possibility of false edge detection as well as prevent colour shift and low contrast. Good quality images are found with objective evaluation. Moreover, different wavelets, thresholds, and decomposition levels have been studied and compared. Time complexity is linear due to wavelet domain analysis which makes the technique fast, reliable, and visually pleasing.
Shadow Detection and Elimination for Robot and Machine Vision Applications
Luma Issa Abdul-Kreem, Hussam k. Abdul-Ameer
Accepted: 2024-03-17
Abstract
Shadow removal is crucial for robot and machine vision as the accuracy of object detection is greatly influenced by the uncertainty and ambiguity of the visual scene. In this paper, we introduce a new algorithm for shadow detection and removal based on different shapes, orientations, and spatial extents of Gaussian equations. Here, the contrast information of the visual scene is utilized for shadow detection and removal through five consecutive processing stages. In the first stage, contrast filtering is performed to obtain the contrast information of the image. The second stage involves a normalization process that suppresses noise and generates a balanced intensity at a specific position compared to the neighboring intensities. In the third stage, the boundary of the target object is extracted, and in the fourth and fifth stages, respectively, the region of interest (ROI) is highlighted and reconstructed. Our model was tested and evaluated using realistic scenarios which include outdoor and indoor scenes. The results reflect the ability of our approach to detect and remove shadows and reconstruct a shadow free image with a small error of approximately 6%.
Back to the Future: Visualization of Development, Problems and Prospects of Artificial Intelligence, Data Science, Quantum Computing
A.V. Tsaregorodtsev, P.V. Revenkov, A.A. Berdyugin
Accepted: 2024-02-10
Abstract
The paper is designed as a review and analysis of the current situation in the field of information technology (IT). The relevance of the article arises from the need to popularize IT among young people, which is reflected in the documents of the Ministry of Digital Development, Communications and Mass Communications of the Russian Federation, as well as from the high demand for experts in the field of digital technologies and the need to increase the digitalization of Russia. According to GeekBrains (the first programming school in Russia, which appeared in 2010, and the leader in the field of training for digital professions, which operates in 85 regions of the Russian Federation and 21 countries of the world), the number of IT job vacancies in this country will grow up to 2 million by 2027. All large organizations are looking for specialists in different IT branches, which are described in this and the following research paper. In this article, which is the first part of the study, the capabilities and problems of the following advanced technologies are considered: artificial intelligence, Data Science and quantum computing. The concepts of technologies are analyzed from the viewpoints of their everyday use and professional application. The topics are closely related and complement each other in one way or another. The article follows the logic and chronology of events in the global IT sphere. The conclusion contains a description of the author's thought experiment about bringing machine intelligence to life, it accumulates the mentioned technologies while taking into account the laws of physics. The calculations for this experiment are given as well. The materials from one of the GeekBrains's educational shows “The Way to IT” were used, including the GIF animation, which is reproduced only on the website of the “Scientific Visualization” journal.
Visualization of Solar Radiation Using Three-Dimensional Computer Graphics Technologies
F.A. Mager, A.V. Sokolova, O.I. Khristodulo
Accepted: 2024-02-05
Abstract
Currently, the prediction, calculation and rationing of solar radiation is a serious problem that has a wide impact on the spheres of human activity. Creating and maintaining a comfortable living environment, as well as solving the world's energy problems, are the fundamental criteria that determine its relevance. This article discusses the possibility of using three-dimensional graphics technologies to calculate insolation. The paper considers an algorithm for calculating the four main components of the visualization of global solar radiation: direct beam radiation, diffuse radiation, reflected beam radiation and reflected diffuse radiation. The freely distributed open source software Blender 3D is used as a tool for working with computer graphics. In the course of the study, calculations based on the principle of bidirectional path tracing, which is used in the visualization algorithms of the Cycles graphics engine, are presented. The use of the technology of transferring complex data to the raster image format allows you to create a separate texture map for each component of the simulated lighting. Based on the obtained texture maps, it is possible to calculate the global solar radiation for all created or imported 3D models in the three-dimensional space of Blender 3D.
Dual-Pass Feature-Fused SSD Model for Detecting Multi-Scale Vehicles on the Construction Site
M. Petrov, S. Zimina, D. Dyachenko, A. Dubodelov, S. Simakov
Accepted: 2023-12-16
Abstract
When detecting equipment on a construction site the objects of detection could have very different scale relative to the image on which they are located. For better detection and bounding box visualization of small objects, a Feature-Fused modification of the SSD detector can be used. Together with the use of overlapping image slicing on the inference, this model copes well with the detection of small objects. However, excessive manual adjustment of the slicing parameters for better detection of small objects can both generally worsen detection on scenes different from those on which the model was adjusted, and lead to significant losses in the detection of large objects and problems with their bound-ing box visualization. Therefore, to achieve the best quality, the image slicing parameters should be automatically selected by the model depending on the characteristic scales of objects in the image.
The article presents a dual-pass version of Feature-Fused SSD for automatic determination of image slicing parameters. To determine the characteristic sizes of detected objects on the first pass, a fast truncated version of the detector is used. On the second pass the final object detection is carried out with slicing parameters selected after the first one. Depending on the complexity of the task being solved, the detector demonstrates a quality of 0.82 - 0.92 according to the mAP (mean Average Precision) metric.
Multiscale Analysis of High Resolution Digital Elevation Models Using the Wavelet Transform
A.N. Zemtsov
Accepted: 2023-11-24
Abstract
A technique is proposed for choosing the optimal wavelet basis in terms of decorrelation of the spectral coefficients of the wavelet basis when solving the problem of representation of digital elevation models. In the course of the work, it was revealed that the selection of the spectral transform basis significantly affects the accuracy of the representation of the original model. The proposed method to the decomposition of digital elevation models based on the discrete wavelet transform does not require large computational costs. A technique is proposed for selection the optimal wavelet basis from the position of the minimum mean square error of the reconstructed signal, when quantizing the high-frequency expansion coefficients. Expressions are obtained for generating scaling and wavelet functions in space. The method developed to represent digital elevation models has good properties, which allows to significantly increase the resolution of digital elevation models in the implemented regional geoinformation system.
Information Environment а for Industrial and Scientific-Cognitive Tourism with Application of GIS
О.А. Ulchitsky, Е.К. Podobreeva, Y.V. Kocherzhinskaya, Е.К. Bulatova, O.M. Veremey
Accepted: 2023-11-24
Abstract
The subject of the stated research is conditioned by the need to develop modern methods and technologies of information support of the tourism industry of the regional profile taking into account its specifics and features. Awareness and comfortable conditions of tourist service are the key factors of successful promotion and sustainable development of this sphere. In the near future, domestic tourism has great prospects, it concerns many territories of the country, and the Southern Urals is no exception.
The article is a continuation of research work related to the collection and analysis of geodata, as well as the visualization of the information environment. This study shows how to graphically visualize information on the basis of the development of an interactive scheme project with the possibility of overlaying it on a scalable satellite map in the field of industrial, scientific-cognitive tourism and architectural tourism on the example of a separate layer "Country of Cities" for the objects located in the South Urals.
In the research on the basis of the program utility "Grid cartogram of reference archaeological objects" the design concept of the interface functionality of utility "KROT-1.0" ("Cartogram of reference objects of tourism. Version 1.0") is developed and tested as an interactive cartogram on Internet platforms.
Methodology wise, the research process consists of 2 stages: pre-project or data collection with the formation of a database catalog and design and research, with the implementation of results, consisting in the development of the design concept of the utility and its integration with a web resource developed on the platform of non-commercial CMS; analysis and comparison of the results obtained on different platforms, publication or placement of the developed interactive schemes on internal servers and Internet platforms with further prospects for the development of mobile applications for the provision of information environment in different spheres of regional tourism.
|
|
|
