Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki (Mar 2020)

METHOD OF IMAGE PROCESSING IN THE PROBLEM OF DETECTING MOVING OBJECTS IN OPTICAL-ELECTRONIC SURVEILLANCE SYSTEMS OF THERMAL IMAGING TYPE

  • E. I. Mikhnionok

DOI
https://doi.org/10.35596/1729-7648-2020-18-2-96-104
Journal volume & issue
Vol. 18, no. 2
pp. 96 – 104

Abstract

Read online

The article considers the method of image processing proposed by the author in relation to the problem of automatic detection of moving objects in optoelectronic thermal imaging systems. Moving objects on the observed scene are subject to investigation, so it is advisable to use algorithms based on background subtraction methods to solve the detection problem. However, the observed objects may include objects of interest (a person, a vehicle), as well as other objects and background elements that increase the noise component of the observed situation. Also, the increase in the noise component is greatly influenced by false segmentation in the foreground of the areas of processed images when transferring the field of view of the sensor of the optical-electronic surveillance system. The purpose of this article is to prove the reduction of the probability of false alarm of an automatic detector due to the author's proposed approaches to image processing. The research uses the mathematical apparatus of probability theory and simulation with subsequent statistical processing of data. The article shows that the probability of a false alarm of an automatic detector based on the background subtraction method increases significantly after the transfer of the field of view of the sensor of the optical-electronic surveillance system and decreases after the movement stops as the areas of the processed image that are falsely highlighted in the foreground are automatically segmented. The simulation showed that the approaches proposed by the author can increase the peak signal-to-noise ratio of processed images and reduce the probability of a false alarm of the automatic detector of objects of interest. The results obtained show the feasibility of adapting detection algorithms based on background subtraction methods to work in scanning optoelectronic surveillance systems.

Keywords