Automatic optical‐to‐SAR image registration using a structural descriptor. Issue 1 (1st January 2020)

• Record Type: Journal Article
• Authors: Paul, Sourabh; Pati, Umesh C.
• Is Part Of: IET image processing. Volume 14:Issue 1(2020)
• Page Start: 62
• Page End: 73
• Publication Date: 2020-01-01
• Subjects: radar imaging -- image registration -- feature extraction -- medical image processing -- synthetic aperture radar; geometric differences -- automatic optical‐to‐SAR image registration -- structural descriptor -- optical‐to‐synthetic aperture radar image registration -- nonlinear intensity variations -- optical images -- optical‐to‐SAR image registration methods -- novel optical‐to‐SAR image registration algorithm -- optical SAR images; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0389
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Optical‐to‐synthetic aperture radar (SAR) image registration is a challenging task in remote sensing as the images have significant non‐linear intensity variations as well as large geometric differences. Moreover, the influence of speckle noise in the SAR image further affects the registration result. The structural descriptors are very effective to handle the non‐linear intensity variations between optical and SAR images. Although a number of optical‐to‐SAR image registration methods have been proposed in the past few years based on the structural information of image, most of them are ineffective for the images having large geometric differences. To address these problems, a novel optical‐to‐SAR image registration algorithm is proposed by using a new structural descriptor. Initially, the corner features are extracted from the optical and SAR images. Then, the proposed structural descriptor is constructed for the extracted features. Finally, feature matching is performed between the optical and SAR images and the correct match are identified. The proposed method is very effective to register the optical and SAR images having significant intensity variations and large geometric differences. It can increase the number of correct match between the images. Experiments on six sets of optical and SAR image pairs demonstrate the effectiveness of the proposed method.