Image Matching of Satellite Data Based on Quadrilateral Control Networks

Abstract

Automatic image matching of satellite data is a difficult process due to the complex characteristics of such image pairs, including significant translation, rotation, scaling and illumination differences. A new method is proposed where, initially, a pre‐registration is performed to coarsely align the input and reference images. Next, a dense set of corner points are extracted using the Harris operator. The strongest conjugate corner points are determined and the accuracy is improved by using least squares matching to construct a precise braced quadrilateral control network in the two images. Once the consistency of the established network pairs has been determined, it is used as a framework to match the remaining corner points. Comprehensive evaluations of the proposed method on a variety of image pairs from different sensors prove its efficiency with sub‐pixel positional accuracy.

VGI and Reference Data Correspondence Based on Location‐Orientation Rotary Descriptor and Segment Matching

“…Recently SIFT‐based methods have been applied in various applications in remote sensing and GIS such as image matching (Sedaghat et al. , ), change detection (Guo‐Rong et al. ), and spatial modeling (Lerma et al.…”

“…The SIFT descriptor is a 3D histogram of image gradient locations and orientations, which is computed by dividing the local image region into 16 (4 × 4) sub-regions, and extracting an 8D histogram of weighted gradient from each. Recently SIFT-based methods have been applied in various applications in remote sensing and GIS such as image matching (Sedaghat et al 2011(Sedaghat et al , 2012, change detection (Guo-Rong et al 2011), and spatial modeling (Lerma et al 2012). The majority of the presented descriptors like SIFT are computed on gray scale images and cannot be used for our application in this article.…”

Very high resolution image matching based on local features and k‐means clustering

“…This gridding process is based on a Harris measure entropyand the number of available corner points in each grid. For a detailed explanation of this method, see Sedaghat et al (2012).…”

Distinctive Order Based Self-Similarity descriptor for multi-sensor remote sensing image matching

“…The main key to this approach is a selection strategy of SIFT features in the full distribution of location and scale where the feature qualities are quarantined based on the stability and distinctiveness constraints. Also in another research we introduced a method for image matching of satellite data based on quadrilateral control networks, which is based on SIFT algorithm and a piecewise model (Sedaghat et al, 2012).…”