Journal Issue: Научная визуализация
Загружается...
Volume
16
Number
3
Issue Date
Journal Title
Journal ISSN
2079-3537
Том журнала
Том журнала
Научная визуализация
(16)
Статьи
Публикация
Открытый доступ
Comparison of the Effectiveness of Using Various Approaches in Detecting Objects on Low-Quality Images
(НИЯУ МИФИ, 2024) Provorova, A.; Polyakova, I.; Kuzmicheva, E.
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.
Публикация
Открытый доступ
Use of 3d Modelling and Printing Capabilities in Students' Project Activities in the Study of Comparative Anatomy of Animals
(НИЯУ МИФИ, 2024) Kolpakova, T. Yu.
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.
Публикация
Открытый доступ
Visually Salient Region Detection in Omnidirectional Images Using Wavelet Textural Feature Map
(НИЯУ МИФИ, 2024) Manisha Mane; Anand Bhaskar
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.
Публикация
Открытый доступ
Modeling the Solution of an Ordinary Differential Equation by the Functional Voxel Method
(НИЯУ МИФИ, 2024) Tolok, A. V.; Tolok, N. B.
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.
Публикация
Открытый доступ
On Visualization When Controlling Wave Structures Using Distributed Heat Sources
(НИЯУ МИФИ, 2024) Alekseev, A. K.; Bondarev, A. E.
For two-dimensional Euler equations, flow control using spatially distributed stationary heat sources is considered. The initial flow, characterized by the interaction of Edney - type shock waves, was changed with the help of heat sources in such a way as to reduce the maximum pressure on the surface of the body. The problem was solved in an optimization formulation using conjugate equations to calculate the gradient of the target functional. In addition to visualizing flow parameters in this problem, it is of interest to visualize the distribution of adjoint parameters and heat sources.