Open AccessDENSE IMAGE MATCHING WITH TWO STEPS OF EXPANSION
Author(s) -
Zuxun Zhang,
Jianan He,
Shan Huang,
YunBo Duan
Publication year - 2016
Publication title -
the international archives of the photogrammetry, remote sensing and spatial information sciences/international archives of the photogrammetry, remote sensing and spatial information sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.264
H-Index - 71
eISSN - 1682-1777
pISSN - 1682-1750
DOI - 10.5194/isprsarchives-xli-b3-143-2016
Subject(s) - feature (linguistics) , epipolar geometry , matching (statistics) , photogrammetry , point (geometry) , computer science , artificial intelligence , point set registration , computer vision , frame (networking) , synthetic aperture radar , image (mathematics) , pattern recognition (psychology) , mathematics , geometry , telecommunications , philosophy , linguistics , statistics
Dense image matching is a basic and key point of photogrammetry and computer version. In this paper, we provide a method derived from the seed-and-grow method, whose basic procedure consists of the following: First, the seed and feature points are extracted, after which the feature points around every seed point are found in the first step of expansion. The corresponding information on these feature points needs to be determined. This is followed by the second step of expansion, in which the seed points around the feature point are found and used to estimate the possible matching patch. Finally, the matching results are refined through the traditional correlation-based method. Our proposed method operates on two frames without geometric constraints, specifically, epipolar constraints. It (1) can smoothly operate on frame, line array, natural scene, and even synthetic aperture radar (SAR) images and (2) at the same time guarantees computing efficiency as a result of the seed-and-grow concept and the computational efficiency of the correlation-based method.