Igor Georgievich Khanykov

Mr. Igor Georgievich Khanykov

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 November 2021 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
VNVadim A. Nenashev
Vadim A. Nenashev
IKIgor Georgievich Khanykov
Igor Georgievich Khanykov
This paper considers the issues of image fusion in a spatially distributed small-size on-board location system for operational monitoring. The purpose of this research is to develop a new method for the formation of fused images of the land surface based on data obtained from optical and radar devices operated from two-position spatially distributed systems of small aircraft, including unmanned aerial vehicles. The advantages of the method for integrating information from radar and optical information-measuring systems are justified. The combined approach allows removing the limitations of each separate system. The practicality of choosing the integration of information from several widely used variants of heterogeneous sources is shown. An iterative approach is used in the method for combining multi-angle location images. This approach improves the quality of synthesis and increases the accuracy of integration, as well as improves the information content and reliability of the final fused image by using the pixel clustering algorithm, which produces many partitions into clusters. The search for reference points on isolated contours is carried out on a pair of left and right images of the docked image from the selected partition. For these reference points, a functional transformation is determined. Having applied it to the original multi-angle heterogeneous images, the degree of correlation of the fused image is assessed. Both the position of the reference points of the contour and the desired functional transformation itself are refined until the quality assessment of the fusion becomes acceptable. The type of functional transformation is selected based on clustered images and then applied to the original multi-angle heterogeneous images. This process is repeated for clustered images with greater granularity in case if quality assessment of the fusion is considered to be poor. At each iteration, there is a search for pairs of points of the contour of the isolated areas. Areas are isolated with the use of two image segmentation methods. Experiments on the formation of fused images are presented. The result of the research is the proposed method for integrating information obtained from a two-position airborne small-sized radar system and an optical location system. The implemented method can improve the information content, quality, and reliability of the finally established fused image of the land surface.

30 March 2021 in Informatics and Automation
Verified
Journal Article
Open access
PDF file
VNVadim A. Nenashev
Vadim A. Nenashev
IKIgor Georgievich Khanykov
Igor Georgievich Khanykov
ИХИгорь Георгиевич Ханыков
Игорь Георгиевич Ханыков
The paper proposes a method for fusioning multi-angle images implementing the algorithm for quasi-optimal clustering of pixels to the original images of the land surface. The original multi-angle images formed by the onboard equipment of multi-positional location systems are docked into a single composite image and, using a high-speed algorithm for quasi-optimal pixel clustering, are reduced to several colors while maintaining characteristic boundaries. A feature of the algorithm of quasi-optimal pixel clustering is the generation of a series of partitions with gradually increasing detail due to a variable number of clusters. This feature allows you to choose an appropriate partition of a pair of docked images from the generated series. The search for reference points of the isolated contours is performed on a pair of images from the selected partition of the docked image. A functional transformation is determined for these points. And after it has been applied to the original images, the degree of correlation of the fused image is estimated. Both the position of the reference points of the contour and the desired functional transformation itself are refined until the evaluation of the fusion quality is acceptable. The type of functional transformation is selected according to the images reduced in color, which later is applied to the original images. This process is repeated for clustered images with greater detail in the event that the assessment of the fusion quality is not acceptable. The purpose of present study is to develop a method that allows synthesizing fused image of the land surface from heteromorphic and heterogeneous images. The paper presents the following features of the fusing method. The first feature is the processing of a single composite image from a pair of docked source images by the pixel clustering algorithm, what makes it possible to isolate the same areas in its different parts in a similar way. The second feature consists in determining the functional transformation by the isolated reference points of the contour on the processed pair of clustered images, which is later applied to the original images to combine them. The paper presents the results on the synthesis of a fused image both from homogeneous (optical) images and from heterogeneous (radar and optical) images. A distinctive feature of the developed method is to improve the quality of synthesis, increase the accuracy and information content of the final fused image of the land surface.

6 October 2022 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
VNVadim A. Nenashev
Vadim A. Nenashev
IKIgor Georgievich Khanykov
Igor Georgievich Khanykov
MKMikhail V. Kharinov
Mikhail V. Kharinov
The paper presents a model of structured objects in a grayscale or color image, described by means of optimal piecewise constant image approximations, which are characterized by the minimum possible approximation errors for a given number of pixel clusters, where the approximation error means the total squared error. An ambiguous image is described as a non-hierarchical structure but is represented as an ordered superposition of object hierarchies, each containing at least one optimal approximation in g0 = 1, 2,..., etc., colors. For the selected hierarchy of pixel clusters, the objects-of-interest are detected as the pixel clusters of optimal approximations, or as their parts, or unions. The paper develops the known idea in cluster analysis of the joint application of Ward’s and K-means methods. At the same time, it is proposed to modernize each of these methods and supplement them with a third method of splitting/merging pixel clusters. This is useful for cluster analysis of big data described by a convex dependence of the optimal approximation error on the cluster number and also for adjustable object detection in digital image processing, using the optimal hierarchical pixel clustering, which is treated as an alternative to the modern informally defined “semantic” segmentation.

18 July 2023 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
IKIgor Georgievich Khanykov
Igor Georgievich Khanykov
VNVadim A. Nenashev
Vadim A. Nenashev
MKMikhail V. Kharinov
Mikhail V. Kharinov
The paper refers to interdisciplinary research in the areas of hierarchical cluster analysis of big data and ordering of primary data to detect objects in a color or in a grayscale image. To perform this on a limited domain of multidimensional data, an NP-hard problem of calculation of close to optimal piecewise constant data approximations with the smallest possible standard deviations or total squared errors (approximation errors) is solved. The solution is achieved by revisiting, modernizing, and combining classical Ward’s clustering, split/merge, and K-means methods. The concepts of objects, images, and their elements (superpixels) are formalized as structures that are distinguishable from each other. The results of structuring and ordering the image data are presented to the user in two ways, as tabulated approximations of the image showing the available object hierarchies. For not only theoretical reasoning, but also for practical implementation, reversible calculations with pixel sets are performed easily, as with individual pixels in terms of Sleator–Tarjan Dynamic trees and cyclic graphs forming an Algebraic Multi-Layer Network (AMN). The detailing of the latter significantly distinguishes this paper from our prior works. The establishment of the invariance of detected objects with respect to changing the context of the image and its transformation into grayscale is also new.

1 June 2020
Verified
Conference Paper
Closed access
IKIgor Georgievich Khanykov
Igor Georgievich Khanykov
VNVadim A. Nenashev
Vadim A. Nenashev
This paper deals with the problem of complexing images formed by the onboard equipment of a multi-position optical-location system. The problem of information aggregation is solved quite difficult in airborne optical-location systems. Therefore, in order to combine data received from high-resolution optical sensors into a single information field, the method based on the developed high-speed method of clustering image pixels is proposed. The purpose of present paper is to develop a method for combining multi-angle images, which is characterized by gradual detailing of clustered images. The result of present paper is a data aggregation technique that allows combining high-resolution multi-angle location images into a single information field with high correlation characteristics as compared to classical algorithms of combining. The practical relevance of paper involves the feasibility of applying the technique of combining digital images for modern optical monitoring systems designed for environmental exploration, forecasting and rapid prevention of natural and man-made emergencies.

4 October 2020 in Proceedings of the Southwest State University
Verified
Journal Article
Closed access
IKIgor Georgievich Khanykov
Igor Georgievich Khanykov
Purpose of research is to apply the modified Ward method in high-speed processing of full-size images of Earth remote sensing.Methods. The classical Ward method is modified by dividing the computational process into three successive stages. At the first stage, a rough hierarchy of approximations is built. At the second stage, an intermediate improvement of the quality of the given partition is performed for a fixed number of colours. At the third stage, the obtained superpixels are clustered using the classical Ward method. The software-algorithmic toolkit consists of four operations on pixel clusters and image segments: merging a pair of clusters into one, dividing a cluster into two original ones, singling out a subset of pixels into a separate cluster and reclassifying some pixels by excluding them from one cluster and assigning them to another. The quality is assessed by the total squared error. Improving the image decomposition quality is ensured by iterative execution of a combination of merging and deviding pixel clusters, image segments, in particular. One of the clusters (segments) is devided in two and a couple of others non-coincident with it are combined into one according to the criterion of minimum increment of the total squared error.Results. The proposed modified Ward method is applied in the processing of full-size images of Earth remote sensing taken from the database of the USC Signal and Image Processing Institute. The results of processing in the modes of pure segmentation and clustering are compared.Conclusion. The proposed pixel clustering model is suitable for high-speed processing of full-size images. Pixel clustering in comparison with image segmentation makes it possible to define in more detail both the contours of objects of interest and their internal structure.