Practical Issues for Real-Time Video Tracking

In this paper we present the algorithm which allows us to have an object tracking close to real time in Full HD videos. The frame rate (FR) of a video stream is considered to be between 5 and 30 frames per second. The real time track building will be achieved if the algorithm can follow 5 or more frames per second. The principle idea is to use fast algorithms when doing preprocessing to obtain the key points and track them after. The procedure of matching points during assignment is hardly dependent on the number of points. Because of this we have to limit pointed number of points using the most informative of them.

Authors:

• Vitaliy Tayanov

Keywords:

• video tracking
• real-time
• Hungarian algorithm
• Full HD video.

References:

[1] Gong, Sh. and Xiang T., Visual Analysis of Behaviour: From Pixels to
Semantics, Springer, London, 2011
[2] Maggio, E. and Cavallaro A., Video Tracking: Theory and Practice,
Wiley, 2011
[3] Marsland, S., Machine Learning: An Algorithmic Perspective, ChapmanHall/
CRC, Boca Raton, Florida, 2009.
[4] Prince, S., Computer Vision : Models, Learning and Inference, Cambridge
University Press, 2012
[5] Bradski G. and Kaehler A., Learning OpenCV, O-Reilly, Sebastopol,
CA, 2008
[6] Chetverikov, D. and Szabo, Zs., "A Simple and Efficient Algorithm for
Detection of High Curvature Points in Planar Curves", Robust Vision
for Industrial Applications 1999, Vol. 128 ,1999, p 175-184.