Methodology for Determining the Required Value of the Image Quality Index for Detection Algorithms under Distortion Conditions
https://doi.org/10.35596/1729-7648-2022-20-3-69-75
Abstract
The article presents an improved technique for determining the required value of the image quality criterion for detection systems operating under distortion conditions. The calculated level of the quality indicator should be used to determine the fact of image distortion. On the basis of the proposed technique, a method of correlation detection in conditions of "smudge" and "defocusing" type distortions has been developed. The developed method of correlation detection is distinguished by the introduction of three stages: identification of distortions in the current image; formation of the convolution core based on the type and parameters of distortion; calculation of the number of iterations based on the required and current value of the image quality criterion. This made it possible to ensure the operation of the correlation detection method in conditions of distortion.
About the Authors
A. Y. Liplianin
Military academy Republic of Belarus
Belarus
Belarus
Liplianin Anton Yur’evich, Lectural at the Department of Automated Control Systems
220057, Minsk, Niezalieznasci Ave., 220
tel. +375-29-504-68-59
A. V. Khiznia
Military academy Republic of Belarus
Belarus
Belarus
Khizniak A.V., Cand of Sci, Assosiate Professor, Leading Researcher of the 2nd Group at the Research Laboratory of the Department of Communications and Automated Control Systems
220057, Minsk, Niezalieznasci Ave., 220
References
1. Liplyanin A.Yu., Khizhnyak A.V., Sergeyenko A.V. Analysis of algorithms for detecting targets in the optical range. Vestnik Polotsokogo gosudarstvennogo universiteta. 2020;12(116):103-108.
2. Liplyanin A.Yu., Khizhnyak A.V., Sergeyenko A.V., Tsarenkov N.V. Substantiation of the criterion for assessing the quality of reconstructing distorted images for an iterative algorithm in correlation detection systems. Dokl. BGUIR. 2019;4(122):64-71.
3. Liplyanin A.Yu., Khizhnyak A.V., Sergeyenko A.V. Investigation of the operation of algorithms for detecting optically observed objects, taking into account the impact of external disturbing factors. Proceedings of the Gomel State University named after F. Skorina. 2021;6(129);77-83.
4. Liplyanin A.Yu., Khizhnyak A.V. A method for restoring images based on automatic calculation of the type, parameters of the distortion function and the required number of iterations. Infocommunication Problems. 2019;1(9);83-90.
5. Bishop C.M. Pattern Recognition and Machine Learning. Springer. 2006.
6. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement. Washington: University of Washington; 2018.
7. Diaz-Ramirez V.H. Picos К., Kober V. Target tracking in nonuniform illumination conditions using locally adaptive correlation filters. Optics Communications. 2014;323;32-43.
8. Wong S. Advanced Correlation Tracking of Objects in Cluttered Imagery. // The Proceedings of SPIE: Acquisition, Tracking and Pointing. 2005;(19).
Review
For citations:
Liplianin A.Y., Khiznia A.V. Methodology for Determining the Required Value of the Image Quality Index for Detection Algorithms under Distortion Conditions. Doklady BGUIR. 2022;20(3):69-75. (In Russ.) https://doi.org/10.35596/1729-7648-2022-20-3-69-75
Views: 291
Email this article 