Approach for multiple moving object detection and tracking

Hello,

I want to know algorithm for multiple moving object detection and tracking in real time. so, I can run this algorithm within 40msec.

In my system, the camera is stationary, a class of methods usually employed is background subtraction. The principle of these methods is to build a model of the static scene (i.e. without moving objects) called background, and then to compare every frame of the sequence to this background in order to discriminate the regions of unusual motion, called foreground (the moving objects).

I have already implemented Background subtraction method and Sigma-Delta estimation method.

Besides this, if anyone has real time algorithm in C or any IEEE paper regarding the same, then please forward me at your earliest.

Thanks & Regards,
Sandip Shah

Re: Approach for multiple moving object detection and tracki

Hi,

Another approach which doesn't need background subtraction or optical flow estimation is mean shift tracking. It works for non-rigid objects and the best paper for this is "Kernel-based mean shift object tracking".

Regards,
CS