A sub-pixel image registration algorithm based on SURF and M-estimator sample consensus

• Published in: Pattern recognition letters Vol. 140; pp. 261 - 266
• Main Authors: Wu, Shulei, Zeng, Wankang, Chen, Huandong
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.12.2020; Elsevier Science Ltd
• Subjects: Algorithms; Computer applications; Fast library for approximate nearest neighbors (FLANN); Feature extraction; Geometric transformation; Image registration; M-estimator sample consensus (MSAC); Matching; Pixels; Point pairs; Registration; Remote sensing; Remote sensors; Speeded up robust features (SURF); Sub-pixel; Sum of squared difference (SSD); Sum of squared difference (SSD); Image registration; Sub-pixel; Speeded up robust features (SURF); Fast library for approximate nearest neighbors (FLANN); M-estimator sample consensus (MSAC)
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2020.09.031

•Proposed the framework of the sub-pixel image registration.•Matching point pairs will be reduced.•Get more anti-interference matches than other methods. Due to the influence of various conditions and uncertain difficulties for remote sensing images, image registration is still a challenging task. Considering the registration accuracy of pixel level cannot satisfy the requirements of some related applications, we put forward a sub-pixel image registration method based on speeded up robust features and M-estimator sample consensus. It mainly involves four aspects. At first, extract sub-pixel level feature points based on SURF algorithm. Next, obtain the initial matching point pairs based on Sum of Squared Difference and Fast Library for Approximate Nearest Neighbors algorithms. And then, remove the mismatched pair of points based on M-estimator sample consensus algorithm. Finally, calculate geometric transformation matrix based on purified matching points to reach sub-pixel accuracy image registration. Experimental results for several remote sensing image pairs with displacement, noise added, rotation, and different sensors, times and sizes, show that the proposed method can get more anti-interference matches than other methods, and take smaller computational cost in registration process.