By Topic

Multiple moving objects detection and tracking based on optical flow in polar-log images

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Hai-Yan Zhang ; Coll. of Inf., Beijing Forestry Univ., Beijing, China

Object detection and tracking are the main research contents of computer vision. One of the methods is based on the estimation of optical flow field, but their calculation result and efficiency are poor. So a multiple object detection and tracking algorithm based on optical flow in polar-log images is proposed in this paper. Optical flow computation is only used in moving area. Firstly, the moving edge is extracted in polar-log coordinate. Secondly, the generalized dynamic image model (GDIM) based method is used and the gradient operator in polar-log coordinate is employed to compute the optical flow directly in every moving area and the object tracking is accomplished. This method has there advantages. One is that the image size reduced and the computing time of optical flow decreased in polar-log coordinate. The other is that the optical flow calculation result is accurate because the GDIM base method is used and the gradient operator in polar-log coordinate is employed. The third is that “excessively smooth” can be resolved by optical flow computation only used in moving area. And this method can be used for multiple objects tracking and real time object tracking. Finally, the experimental results prove that the proposed method in the paper is efficient to multiple objects detection and tracking.

Published in:

Machine Learning and Cybernetics (ICMLC), 2010 International Conference on  (Volume:3 )

Date of Conference:

11-14 July 2010