Journal
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
Volume 68, Issue -, Pages 40-55Publisher
ELSEVIER
DOI: 10.1016/j.isprsjprs.2011.12.005
Keywords
Image matching; Point matching; Edge matching; Triangle constraint; Self-adaptive propagation
Categories
Funding
- Research Grants Council of Hong Kong [PolyU 5312/10E]
- Start-up Research Fund Program [1-ZV6K]
- Hong Kong Polytechnic University [A-PJ62]
- National Basic Research Program of China/973 Program [2010CB731801]
- National Natural Science Foundation of China [41021061]
Ask authors/readers for more resources
This paper presents an innovative image matching method for reliable and dense image matching on poor textural images, which is the integrated point and edge matching based on the self-adaptive edge-constrained triangulations. Firstly, several seed points and seed edges are obtained on the stereo images, and they are used to construct a pair of initial edge-constrained triangulations on the images. Then, points and edges are matched based on the triangle constraint and other constraints. The newly matched points and edges are inserted into the triangulations and the constrained triangulations are updated dynamically along with the matching propagation. The final results will be the final edge-constrained triangulations generated from the successfully matched points and edges. Experiments using typical space-borne, airborne, and terrestrial images with poor textures revealed that the integrated point and edge matching method based on self-adaptive triangulations is able to produce dense and reliable matching results. Moreover, from the final matched points and edges, 3D points and edges preserving the physical boundaries of objects can be further derived based on photogrammetric techniques, which is ideal for further object modeling applications. (C) 2011 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available