Improving Piecewise Linear Registration of High-Resolution Satellite Images Through Mesh Optimization

Abstract

Piecewise linear transformation is a powerful technique for coping with the registration of images affected by local geometric distortions, as it is usually the case of high-resolution satellite images. A key point when applying this technique is to divide the images to register according to a suitable common triangular mesh. This comprises two different aspects: where to place the mesh vertices (i.e., the mesh geometrical realization) and to set an appropriate topology upon these vertices (i.e., the mesh topological realization). This paper focuses on the latter and presents a novel method that improves the registration of two images by an iterative optimization process that modifies the mesh connectivity by swapping edges. For detecting if an edge needs to be swapped or not, we evaluate the registration improvement of that action on the two triangles connected by the edge. Another contribution of our proposal is the use of the mutual information for measuring the registration consistency within the optimization process, which provides more robustness to image changes than other well-known metrics such as normalized cross-correlation or sum of square differences. The proposed method has been successfully tested with different pairs of panchromatic QuickBird images (0.6 m/pixel of spatial resolution) of a variety of land covers (urban, residential, and rural) acquired under different lighting conditions and viewpoints.

Optical Flow Inversion for Remote Sensing Image Dense Registration and Sensor's Attitude Motion High-Accurate Measurement

“…Generally, most of them concentrated on several simple deforming forms such as affine, shear, translation, rotation, or their combinations instead of investigating more sophisticated dynamic deforming models. In [26][27][28][29][30], some effective approaches have been proposed to increase the accuracy and the robust of algorithms according to the respective reasonable models according to the specific properties of objective images.…”

Improved Piecewise Linear Transformation for Precise Warping of Very-High-Resolution Remote Sensing Images

“…The sensed image is warped to the geometric location of the reference image through non-linear transformation models such as thin-plate spline, multiquadric, local weighted mean (LWM), and piecewise linear (PL) used for VHR image warping [12,13]. Among these, PL transformation is widely used because of its superior performance as compared to the other warping methods [12,14,15].…”

“…Therefore, most of the studies that use PL transformation for warping have considered the warping result only from the region inside the convex hulls [18][19][20][21][22]. Research on improving PL transformation by revising the triangular construction algorithm [14] or by combining it with other warping transformations [11,23] has been conducted, but these approaches have not offered a fundamental solution to the intrinsic problem of PL transformation. Therefore, research focusing on minimizing the distortion occurring outside the image boundary is necessary to effectively exploit PL transformation.…”

Automated Geo/Co-Registration of Multi-Temporal Very-High-Resolution Imagery

“…Although georegistration based on the bias-compensation of RPCs is conducted, VHR multi-temporal images still show a local misalignment because of dissimilarities in the image acquisition conditions, such as the stability of the acquisition platform, the off-nadir angle of the sensor, and the relief displacement of the considered scene [ 21 ]. To solve these problems, a large number of CPs in regions where local misalignments are severe should be detected, after which non-rigid transformation models to mitigate the local distortions should be used [ 22 , 23 , 24 , 25 ]. However, obtaining evenly distributed CPs over the entire image is difficult, and thus these models cannot completely solve the problem.…”