By Topic

Moving objects detection from time-varied background: an application of camera 3D motion analysis

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
$33 $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

2 Author(s)
Zhencheng Hu ; Dept. of Comput. Sci., Kumamoto Univ., Japan ; K. Uchimura

Motion detection from a moving observer is a very important technique for 3D dynamical image analysis. Because of continuous background variations, detecting real moving objects has become very difficult and employs an optical flow method to measure the flow vector difference between the background and moving objects. Unfortunately, there is a huge calculation cost for obtaining accurate optical flow vectors. A new motion detecting method based on camera 3D motion analysis is proposed. With the special motion features of an on-board camera and FOE, our method can detect real moving objects simply by matching two adjacent frames. The camera 3D motion can theoretically be determined in our method with only three matching pairs, which makes it fast and more efficient for real-time applications

Published in:

3-D Digital Imaging and Modeling, 1999. Proceedings. Second International Conference on

Date of Conference: