Far East Journal of Experimental and Theoretical Artificial Intelligence
Volume 3, Issue 2 (Special Issue on 13th Conference on Artificial Intelligence and Applications (TAAI 2008), Pages 69 - 80
(May 2009)
|
|
MOVING OBJECT DETECTION AND TRACKING USING GMM
Hwei-Jen Lin (Taiwan), Jih Pin Yeh (Taiwan), Chun-Wei Wang (Taiwan) and Feng-Ming Liang (Taiwan)
|
Abstract:
For object detection and tracking we use a modified version of Gaussian Mixture Models (GMMs) to construct the background, and then subtract it from the image to obtain the foreground where the moving objects are located. We then perform some operations, including shadow removal, edge detection, and connected component analysis to localize each moving object in the foreground.
As soon as an object is detected it is tracked in the subsequent frames using a Particle Filter (PF). The PF is effective, but the dimension of its state space is high since the tracked objects tend shift. To reduce this problem we modify the particle filter by tracking over the foreground portion instead of the entire image. Using modified versions of both the GMM and PF, our system proves to have a high accuracy rate for detection/tracking and satisfactory time efficiency. |
| Keywords and phrases: detection, tracking, Gaussian mixture model (GMM), particle filters (PF), sequential K-mean algorithm, expectation maximization (EM). |
| |
| Number of Downloads: 159 | Number of Views: 489 |
|
