Region growing stereo matching method for 3D building reconstruction
by Gaurav Gupta, M.S. Rawat, R. Balasubramanian, Rama Bhargava, B.G. Krishna
International Journal of Computational Vision and Robotics (IJCVR), Vol. 2, No. 1, 2011

Abstract: This paper presents a new stereo matching algorithm based on region growing algorithm. To avoid visiting the entire disparity space, an algorithm has been proposed that greedily grow the corresponding patches from a given set of reliable seed correspondences. The proposed algorithm is using regions as matching primitives and defines the corresponding region energy functional for matching by utilising matching technique. Initially, a pre-matching technique i.e., Harris corner detector is used to obtain the initial matching points called, seed points. Secondly, a local window-based matching method is used to determine the disparity estimate from an initial set of seeds. Finally mode filter technique fills the gap of insufficiency of the sparse disparity for whole surface reconstruction. The results show that the proposed scheme is reliable, accurate and robust to high resolution aerial images. The proposed approach is very useful in 3D city model as buildings are the most important objects in producing a 3D city model.

Online publication date: Thu, 31-Mar-2011

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Vision and Robotics (IJCVR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com