Abstract
Image registration of remotely sensed imagery is challenging, as complex deformations are common. Different deformations, such as affine and homogenous transformation, combined with multimodal data capturing can emerge in the data acquisition process. These effects, when combined, tend to compromise the performance of the currently available registration methods. A new image transform, known as geometric mean projection transform, is introduced in this work. As it is deformation invariant, it can be employed as a feature descriptor, whereby it analyzes the functions of all vertical and horizontal signals in local areas of the image. Moreover, an invariant feature correspondence method is proposed as a point matching algorithm, which incorporates new descriptor’s dissimilarity metric. Considering the image as a signal, the proposed approach utilizes a square Eigenvector correlation (SEC) based on the Eigenvector properties. In our experiments on standard test images sourced from “Featurespace” and “IKONOS” datasets, the proposed method achieved higher average accuracy relative to that obtained from other state of the art image registration techniques. The accuracy of the proposed method was assessed using six standard evaluation metrics. Furthermore, statistical analyses, including t-test and Friedman test, demonstrate that the method developed as a part of this study is superior to the existing methods.
Highlights
Remote sensing is the method of obtaining information from objects or areas remotely, for example capturing earth imagery from aircraft, satellites or unmanned aerial vehicles (UAV) [1]
The reference and the target images are considered as the input of the registration method, while the output is the recovered target image, which should be as much as possible similar to the reference image
Geometric feature descriptor and dissimilarity based registration we need to examine the similarity between the recovered image and the reference image
Summary
Remote sensing is the method of obtaining information from objects or areas remotely, for example capturing earth imagery from aircraft, satellites or unmanned aerial vehicles (UAV) [1]. Geometric feature descriptor and dissimilarity based registration the extant methods are based on rigid bodies of images that are utilized to extract transformation information for registration [3] These methods cannot achieve appropriate results to register images with high deformations. These weaknesses are considered in this study, the aim of which was to overcome the limitations This is achieved by using a new method to extract the key points in different images, as well as applying an improved dissimilarity metric to find the correspondence points and estimate the transformation parameters. Myronenko and Song [5] reformulated registration as a probability density estimation problem While their method produces better results compared to other techniques, the method failed to register images with complex information and those affected by high transformation. The main contribution of this study stems from the development of an accurate feature correspondence method as an image registration technique based on a new dissimilarity metric and a novel approach for extracting the most accurate correspondence points using a line based feature extraction technique
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
