Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/2608
Title: Coarse-to-Fine Registration of Remote Sensing Optical Images using SIFT and SPSA Optimization
Authors: Paul, Sourabh
Pati, Umesh C
Keywords: Image registration
Scale invariant feature transform (SIFT)
Simultaneous perturbation stochastic approximation (SPSA)
Issue Date: Dec-2016
Citation: International Conference on Soft Computing: Theories and Applications(SoCTA 2016), Amity University Rajasthan, Jaipur, India, 28-30 December 2016
Abstract: Sub-pixel accuracy is the vital requirement of remote sensing optical image registration. For this purpose, a coarse-to-fine registration algorithm is proposed to register the remote sensing optical images. The coarse registration operation is performed by the scale-invariant feature transform (SIFT) approach with an outlier removal method. The outliers are removed by the Random sample consensus (RANSAC) algorithm. The fine registration process is performed by maximizing the mutual information between the input images using the first order simultaneous perturbation stochastic approximation (SPSA) along with the second order SPSA. To verify the effectiveness of the proposed method, experiments are performed by using three sets of optical image pairs.
Description: Copyright belongs to the proceeding publisher
URI: http://hdl.handle.net/2080/2608
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2016_SoCTA_SPaul_Coarse-to-Fine.pdf702.96 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.