Premium
Line‐based modified iterated Hough transform for automatic registration of multi‐source imagery
Author(s) -
Habib Ayman F.,
Alruzouq Rami I.
Publication year - 2004
Publication title -
the photogrammetric record
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.638
H-Index - 51
eISSN - 1477-9730
pISSN - 0031-868X
DOI - 10.1111/j.0031-868x.2003.00254.x
Subject(s) - artificial intelligence , hough transform , computer vision , image registration , computer science , transformation (genetics) , robustness (evolution) , similarity measure , geometric transformation , similarity (geometry) , pattern recognition (psychology) , image (mathematics) , biochemistry , chemistry , gene
Image registration aims at combining imagery from multiple sensors to achieve higher accuracy and derive more information than that obtained from a single sensor. The enormous increase in the volume of remotely sensed data that is being acquired by an ever‐growing number of earth observation satellites mandates the development of accurate, robust, and automated registration procedures. An effective automatic image registration has to deal with four issues: registration primitives, transformation function, similarity measure, and matching strategy. This paper introduces a new approach for automatic image registration using linear features as the registration primitives. Linear features have been chosen because they can be reliably extracted from imagery with significantly different geometric and radiometric properties. The modified iterated Hough transform (MIHT), which manipulates the registration primitives and similarity measure, is used as the matching strategy for automatically deriving an estimate of the parameters involved in the transformation function as well as the correspondence between conjugate primitives. The MIHT procedure follows an optimal sequence for parameter estimation that takes into account the contribution of linear features with different orientations at various locations within the imagery towards the estimation of the transformation parameters in question. Experimental results using real data proved the feasibility and robustness of the suggested approach.