TRACKING OF LOW-SIZED TARGETS FROM NON-STATIONARY CAMERA BASED ON COVARIANCE FEATURES AND PREDICTOR
Abstract
A fast selective-covariance tracking method of low-sized targets from non-stationary camera is proposed. It is based on selective predictor and representation of spatial and statistical target properties by covariance matrix. The comparison of proposed selective-covariance and known covariance methods is provided.
About the Authors
I. A. Baryskievic
Белорусский государственный университет информатики и радиоэлектроники
Belarus
Belarus
V. Yu. Tsviatkou
Белорусский государственный университет информатики и радиоэлектроники
Belarus
Belarus
References
1. Porikli F., Tuze O. // Proceedings of IEEE Int’l. Conference on Multimedia and Expo. 2005. P. 1234-1237.
2. Avidan S. // Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 2005. Vol. 2. P. 494-501.
3. Ribaric S., Adrinek G., Segvic S. // Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference. 2004. P. 231-234.
4. Tuzel O., Porikli F., Meer P. // Proc. 9th European Conf. on Computer Vision. 2006. Vol. 2. P. 589-600.
Review
For citations:
Baryskievic I.A., Tsviatkou V.Yu. TRACKING OF LOW-SIZED TARGETS FROM NON-STATIONARY CAMERA BASED ON COVARIANCE FEATURES AND PREDICTOR. Doklady BGUIR. 2014;(3):33-39. (In Russ.)
Views: 330
Email this article 