This email address is being protected from spambots. You need JavaScript enabled to view it.
 
+7 (4912) 72-03-73
 
Интернет-портал РГРТУ: http://rsreu.ru

UDC 004.932

THE ALGORITHM OF VIDEO SEQUENCE SHAKE SUPPRESSION USING MODIFIED TOOL FOR SEARCH AND EXTRACTION OFFEATURE POINTS CONSTELLATIONS 

S. N. Kirillov, PhD (technical sciences), Full Professor. Head of radio control and communications department, RSREU, Ryazan, This email address is being protected from spambots. You need JavaScript enabled to view it.;
I. V. Kostkin, PhD (technical sciences), Associate Professor of radio control and communications department, RSREU, Ryazan, This email address is being protected from spambots. You need JavaScript enabled to view it.;
A. V. Elyutin, Undergraduate student of radio control and communications department, RSREU, Ryazan, This email address is being protected from spambots. You need JavaScript enabled to view it.

The problem of video frame shake suppression using software resources is considered in this paper. The purpose of this paper is to develop software algorithm of video sequence shake suppression to achieve the most comfortable conditions of visual perception, and to improve the efficiency of video compression codecconverted video sequence.
Software algorithm for video frame sequence from static cameras is presented. The algorithm is based on the tool of selection, comparison and analysis feature points of video frames. It’s proved that construction of feature points constellations decreases computing costs to 5 times in comparison with common feature points detection method.
Experimental researches of developed algorithm are presented. They show results of frame shaking decrease by 10% to 0.3% horizontally (relative to the horizontal size of the image) and by 9% to 0.5% vertically (relative to the vertical size of the image). Moreover it is presented that time used for enhanced video compression by H.264 video codecs 1.5 times decreases.
Key words: video shake suppression, video processing, feature points, constellation of feature points.

 Скачать статью