• Home
  • Alexander B. Murynin
Alexander B. Murynin

Alexander B. Murynin
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences

PhD

About

66
Publications
3,193
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
167
Citations

Publications

Publications (66)
Article
Full-text available
The development and validation of a method for remote measurement of the spectra of sea waves, which significantly expands the capabilities to study surface waves in large water areas in a wide range of wavelengths, is described. The applied approach is based on the use of retrieving operators, which are constructed by the method of numerical simul...
Article
A method has been developed for constructing three-dimensional models of rigid objects on the earth’s surface using one satellite image using the example of railway infrastructure. The method consists in step-by-step processing of satellite images with sequential application of two convolutional neural networks. In the first processing step, a sate...
Article
The paper describes a method for constructing three-dimensional models of rigid objects from one satellite image, based on the use of two convolutional neural networks. The first neural network detects an object of a given physical class (integral image analysis), the second works in the locations of areas in the image, identified by the results of...
Article
A probabilistic method for improving the spatial resolution of multispectral space images using a reference image is proposed. The developed method calculates the mathematical expectation of pixel brightness in different channels of an improved multispectral image based on the probabilistic characteristics of the pixel neighborhood on the multispec...
Article
Full-text available
The paper proposes a method for recognition of earth surface types according to space images using object-oriented classification. The classification is conducted in two stages: Markov stochastic segmentation for object extraction and supervised classification of the objects. The method is tested on space imagery of the Russian Arctic in comparison...
Article
The study tested two methods of image enhancement using spectral representations. The first approach is based on the assumption that the required information about the high spatial resolution details is obtained from the additional reference image. High-resolution image is constructed using a combination of spatial spectra of the main and reference...
Article
An approach to the retrieval of sea wave spatial spectra based on satellite optical imagery in linear and nonlinear approximations is described. Physical mechanisms of the formation of disturbed sea surface brightness fields recorded by remote sensing equipment are analyzed. Wave spectra retrieval methods using brightness field formation models tha...
Article
The results of studying sea-wave spectra in a wide wavelength range using high resolution (0.5–1.0 m) satellite optical imagery spectra and the results of measurements carried out from an oceanographic platform using string-wave recorders, stereo system, and drifting wave buoys are presented in this paper. The wave spectra retrieved from satellite...
Article
A method to register sea-wave spectra using optical aerospace imagery has been developed. The method is based on the use of retrieval operators both in areas of high and low spatial frequencies, including the areas of spectral maximum. The approach to adjust and validate the method developed using sea truth data obtained by string wave recorders ha...
Article
In this research we explore methods of image quality improvement using spatial spectral representation and describe two formulations of the problem. In the first one the information on high-resolution details is available from the additional reference image. High-resolution image is obtained by combining the spectra of the source and reference imag...
Article
Full-text available
Two methods for improving images using spectral representations are considered. The first approach is based on the assumption that details of a high spatial resolution specified by an additional reference image are known. A high resolution image is constructed using the combined spatial spectra of the main and reference images. Additional informati...
Article
Full-text available
The algorithm for detecting cars in color images obtained by aerophotography has been presented. The approach is as follows: the majority of cars are painted in one color and have similar sizes. This makes possible to separate cars in the background as areas with color characteristics that differ from the background and have a certain size and form...
Article
Full-text available
A method for predicting the characteristics of areas subject to the anthropogenic impact according to the Earth’s remote sensing data is proposed. The developed method is based on the identification of patterns using long-term periodic observations. These patterns are applied to the seasonal observations of the current year. The method is implement...
Conference Paper
Full-text available
One of the reasons of such vision pathology as human stereoscopic vision capability dysfunction is an asymmetry of a human face. As a rule, such dysfunctions occur as early as in the babyhood, when diagnostic methods applied for adults are ineffective. Early diagnostics and prophylaxis could help in treatment of such pathology and face 3D modeling...
Conference Paper
Full-text available
The paper presents an algorithm for detecting automobiles in color images obtained by aerial photography. The key to the solution is that majority of automobiles are painted in single color and have similar size and shape. This allows discriminating areas occupied by vehicles from the background as regions with certain color characteristics and geo...
Conference Paper
Full-text available
A new method for predicting characteristics of landsurface objects has been proposed. The method is based on finding annual periodical patterns and comparison with a pattern obtained for year of observation. An example of the method application is considered. In the example authors propose, train and test a model for forecasting of crop yields base...
Conference Paper
Full-text available
Agricultural yields can be predicted from detailed multi-year remote sensing image sequences using measured features of vegetation conditions. In this paper, the dependency between the moment of prediction and the accuracy of the forecast is studied. The linear model is selected as a basic approach of yield forecasting. Then, the model is extended...
Conference Paper
Full-text available
Availability of detailed multi-year remote sensing image sequences allows finding a relation between the measured features of vegetation condition history and agricultural yields. The large image sequence over 10 years is used to build and compare 4 yield prediction models. The models are developed trough gradual addition of complexity. The initial...
Article
Development of biometric human identification algorithms and systems is reviewed. A crisis that prevents them from being used in large computing systems is demonstrated. Comprehensive reliable tests are considered as a way to overcome the crisis. Ways to take into account the influence various factors may have on the reliability of evaluating the p...
Article
A primary consideration of this paper is to determine different factors influencing the reliability of performance evaluations of remote person recognition algorithms and systems. The authors suggest a method for determining and computing quantitative quality criteria of multimodal biometric data and consider the possibility of extrapolating test r...
Article
We present a system for estimating the quality of polyurethane foam, which is able to measure the apparent density and mean size of the cell. The system consists of a flatbed scanner of high resolution, an electronic balance, and a personal computer. We present the new way for measuring the sample volume using six nonorthogonal projections and adap...
Article
Full-text available
One of the most popular and practically valuable problems in the field of pattern analysis and machine intelligence is human face recognition. A computer vision system for identification of human faces is presented. The system is designed as an automatic checkpoint. Two scenarios of system behavior are developed. The first one assumes verification...
Article
Full-text available
One of the crucial problems in machine vision is reconstruction of 3D shape of objects from their images and the most complicated aspect of this problem is disparity estimation. Some techniques of disparity calculation in real-time monocular and binocular environment are presented. The developed algorithms are based on the correlation method of cal...
Article
Prompt and delayed neutrons and secondary γ rays are the informational radiation in the photonuclear technology for recording fissile materials. Due to the high cost of detectors and difficulties in their placing around a container, it is desirable that the same detectors be used to record all kinds of informational radiation. The design of a multi...
Article
The purpose of the present work is to investigate numerically the energy-time characteristics of γ and neutron radiation emitted from strongly screened fissile substances irradiated by pulsed bremsstrahlung. It is shown that when fissile materials are screened by a metal with a small or medium atomic number (e.g., aluminum and iron) the prompt and...
Article
Full-text available
Problem of human vision pathology diagnostics is being studied with the aid of computer vision technology. Hardware-software complex developed for this research is described. Several face asymmetry evaluation algorithms are analyzed. Relationship between asymmetry measure and medical diagnosis data is investigated.
Article
Full-text available
The problem of automatic detection of regions of interest (ROI) on color photos is considered. The efficiency of Viola-Jones face detector implemented in Intel OpenCV library is analyzed. The image size dependence of the algorithm characteristics is studied. It is shown that there are 2 significant drawbacks of this face detection algorithm as appl...
Article
Full-text available
The principles for designing multimodal biometric systems for improving the reliability of human recognition systems are discussed. The problem is solved by the example of a combination of two biometric human features that can be obtained without any contact with the registering sensor, namely, face images and records of the human voice. The identi...
Conference Paper
We propose a comparative research analysis of two major approaches to 2D face detection problem - local feature invariant approach and appearance-based approach. The local feature invariant approach is represented by the algorithm based on Gabor wavelets and geometry estimation. The appearance-based approach is represented by SNoW neural networks....
Article
The basic principles of constructing a gradient filter for extracting contour features of objects in images are considered. A gradient filter based on the gradient of the Gaussian and that allows one to extract contour features in various spatial frequency ranges is considered. An algorithm for adaptive adjustment of the filter for the optimal dete...
Article
Basic principles of designing a robot Stereovision system are described. Basic principles of stereopsys are considered. Algorithms of image preprocessing and stereo matching are presented. The methods of enhancing the reliability of measurements are analyzed, and an algorithm for correcting uncertain measured data is proposed. A principle of partit...
Article
Full-text available
В статье рассмотрены основные принципы построения градиентного фильтра для выделения контурных признаков объектов на изображении. Рассмотрен градиентный фильтр на основе градиента гауссиана, позволяющий выделять контурные признаки в различных пространственных частотных диапазонах. Предложен алгоритм адаптивной настройки фильтра для оптимального выд...
Article
Full-text available
A biometric access control system based on identification of human face is presented. The system developed performs remote measurements of the necessary face features. Two different scenarios of the system behavior are implemented. The first one assumes the verification of personal data entered by visitor from console using keyboard or card reader....
Article
Full-text available
Development of computer vision systems raises a problem of creating effective methods for restoring surface characteristics from their photographic images minimizing calculations while preserving reasonable accuracy of measurements. Here optimized algorithms of the surface reconstruction from stereo-images is proposed. The optimization is achieved...
Article
Full-text available
Work presented suggests a combined informational space and decision rule for recognition of 3-D objects. The informational space consists of heterogeneous sets of features (i.e. belonging to different spaces), that are object images, images of certain object features and 3-D object surface representation. Decision rule for recognition in this combi...
Article
Principles for the construction of automatic recognizing systems that use stereoscopic vision are discussed. Methods, algorithms, and software are developed for person identification on the basis of stereo images of faces. These facilities are implemented in research prototypes of an automatic recognizing system on the basis of a personal computer....
Article
Full-text available
The problem of recovering the shape of a three-dimensional surface by using stereo images is solved. On the basis of the correlation method, an efficient algorithm of calculating disparity and finding the corresponding points on pairs of stereo images is developed. Algorithms optimized with respect to computational performance and adaptable to the...
Article
Full-text available
The problem of recovering the shape of a three-dimensional surface by using stereo images is solved. On the basis of the correlation method, an efficient algorithm of calculating disparity and finding the corresponding points on pairs of stereo images is developed. Algorithms optimized with respect to computational performance and adaptable to the...
Article
A method of reconstruction sea wave heights spectra using the nonlinear model of transfer function relating wave slopes with sea surface images is developed. The method includes the numerical simulation of optical images under various illumination conditions and the synthesis of the spatial-frequency 2-D filters for reconstruction of sea-surface sl...
Article
The paper describes an experimental method for checking the adequacy of remote measurement of spectra of a sea disturbance in the gravitational and gravitational/capillary bands by comparison of contact and stereo photogrammetric measurements. -Authors

Network

Cited By

Projects

Project (1)
Archived project