PROJECT TITLE :
A Novel Subpixel Phase Correlation Method Using Singular Value Decomposition and Unified Random Sample Consensus
Subpixel translation estimation using part correlation could be a fundamental task for various applications within the remote sensing community. The foremost drawback of the present subpixel phase correlation methods lies in their sensitivity to corruption, together with aliasing and noise, also as the poor performance in the case of practical remote sensing data. This paper presents a completely unique subpixel section correlation method using singular price decomposition (SVD) and the unified random sample consensus (RANSAC) algorithm. Within the proposed methodology, SVD theoretically converts the translation estimation problem to one dimensions for simplicity and potency, and also the unified RANSAC algorithm acts as a sturdy estimator for the line fitting, in this case for the high accuracy, stability, and robustness. The proposed technique integrates the benefits of Hoge's technique and therefore the RANSAC algorithm and avoids the corresponding shortfalls of the original phase correlation method based solely on SVD. A pixel-to-pixel dense matching scheme on the idea of the proposed method is also developed for practical image registration. Experiments with both simulated and real information were meted out to test the proposed technique. In the simulated case, the comparative results estimated from the generated artificial image pairs indicate that the proposed method outperforms the other existing methods within the presence of each aliasing and noise, in each accuracy and robustness. Moreover, the pixel locking result that commonly occurs in subpixel matching was conjointly investigated. The degree of pixel locking effect was found to be significantly weakened by the proposed method, as compared with the initial Hoge's technique. In the real data case, experiments using different bands of ZY-3 multispectral sensor-corrected pictures demonstrate the promising performance and feasibility of the proposed methodology, that is able to spot seams of the image stitching between sub-charge-coupled device units.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here