UDC 004.932
METHOD FOR DETECTING OBJECTS WITH ADDITIONAL SEMANTIC SIGNATURE
A. I. Novikov, Dr. Sc. (Tech.), associate Professor department of higher mathematics RSREU, Ryazan, Russia;
orcid.org/0000-0002-8166-8234, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
D. I. Ustukov, Lecturer, Department of computing machines, RSREU, Ryazan, Russia;
orcid.org/ 0000-0002-4848-8936, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The aim of the work is to develop a method for detecting objects in the image of Earth underlying surface
which have additional semantic feature in the form of one or more rectilinear sections as part of object
contour on contour image. The presence and the type of additional feature made it possible to develop the
technology for processing a raster image with minimal computational complexity. The proposed technology
consists of four main stages: nonlinear filtering of discrete white noise using a modified version of sigma
filter which allows the boundaries of objects to be preserved without blurring; selection of object contours;
search for straight sections as part of contour lines followed by piecewise linear approximation of nonlinear
part of closed contours; detection and identification of objects of interest based on calculating contour autocorrelation
function.
Key words: noise variance estimation, sigma filter, edge detection, line detection, method of second derivatives,
contour autocorrelation function.