ANALYSIS OF ALGORITHMS FOR DETECTING MOVING OBJECTS IN THE VIDEO IMAGE

The problem related to the detection of objects on video images, has many practical applications related to security issues, information processing in virtual reality, management of mobile robots, etc. The paper considers the most frequently used methods of allocation moving objects in relation to video sequences obtained from household cameras in the presence of noise in images. The main features of object detection are shown. The characteristics of the main methods used for the analysis are described: the method of background subtraction, the method of time difference, the method of optical flow. The main problems of processing video sequences are identified, the impossibility of using classical methods is described, and ways to improve the quality of moving objects are proposed. The table of comparative analysis of methods is given: time spent on calculation, accuracy of detection, advantages and disadvantages. There is also a table comparing the success of methods when detecting objects, which specifies the percentage of successful object definition at a given video resolution and a certain environment. It has been demonstrated that video resolution has a noticeable effect on the success of the detection of moving objects, as the higher the resolution, the more preliminary information for processing the algorithm has in each frame.

1. Manisha Chate Object Detection and tracking in Video Sequences / Manisha Chate, S.Amudha, Gohokar Vinaya // ACEEE Int. J. on Signal & Image Processing, Vol. 03, No. 01, Jan 2012.

2. Anaswara S Mohan Video Image Processing for Moving Object Detection and Segmentation using Background Subtraction / Anaswara S Mohan, R.Resmi // IEEE International Conference on Computational Systems and Communications (ICCSC), Vol. 01, no. 01, pp.288-292, 17-18 Dec 2014.

3. Weiming Hu. A Survey on Visual Surveillance of Object Motion and Behaviors / Weiming Hu, Tieniu Tan,Liang Wang, and Steve Maybank // IEEE Transactions on systems, man, and cybernetics applications and reviews, vol. 34, no. 3, pp. 334- 352, August 2004

4. Lychkov I. I. Otslezhivanie dvizhushchikhsya ob"ektov dlya monitoringa transportnogo potoka / I. I. Lychkov, A. N. Alfimtsev, V. V. Devyatkov // (http://itas2011.iitp.ru/pdf/1569457725.pdf)

5. Singla M. Motion Detection Based on Frame Difference Method International / M.Singla // Journal of Information & Computation Technology. 2014. Vol. 4. No. 15. P. 1559–1565.

6. Zivkovic Z. Improved adaptive gaussian mixture model for background subtraction / Z.Zivkovic // IEEE Int. Conf. Pattern Recognition. 2004. Vol. 2. P. 28–31

7. Bouwmans T. Background Modeling using Mixture of Gaussians for Foreground Detection – A Survey / T. Bouwmans, El Baf F., B.Vachon // Recent Patents on Computer Science. 2008. Vol. 1. P. 219– 237.

8. Asim R. Aldhaheri Detection and Classification of a Moving Object in a Video Stream / Asim R. Aldhaheri and Eran A. Edirisinghe // Proc. of the Intl. Conf. on Advances in Computing and Information TechnologyACIT, 2014.

9. Gordin M. S. Algoritmy obnaruzheniya trevozhnykh sobytiy dlya sistem avtomatizirovannogo videonablyudeniya / M. S. Gordin, S. A. Ivanov.// Vestnik NGU: sb. statey. – Novosibirsk, 2017. – Vyp. 3.

10. Kozlov V.A. Analiz metodov vydeleniya dvizhushchikhsya ob"ektov na videoposledovatel'nosti s shumami / V.A. Kozlov, A.S. Potapov // Nauchno-tekhnicheskiy vestnik Sankt-Peterburgskogo gosudarstvennogo universiteta informatsionnykh tekhnologiy, mekhaniki i optiki: sb. statey. – Sankt-Peterburg, 2011. ¬¬– Vyp. 73.