Automatic Registration Method for Optical Remote Sensing Images with Large Background Variations Using Line Segments

Abstract

Abstract:Image registration is an essential step in the process of image fusion, environment surveillance and change detection. Finding correct feature matches during the registration process proves to be difficult, especially for remote sensing images with large background variations (e.g., images taken pre and post an earthquake or flood). Traditional registration methods based on local intensity probably cannot maintain steady performances, as differences are significant in the same area of the corresponding images, and ground control points are not always available in many disaster images. In this paper, an automatic image registration method based on the line segments on the main shape contours (e.g., coastal lines, long roads and mountain ridges) is proposed for remote sensing images with large background variations because the main shape contours can hold relatively more invariant information. First, a line segment detector called EDLines (Edge Drawing Lines), which was proposed by Akinlar et al. in 2011, is used to extract line segments from two corresponding images, and a line validation step is performed to remove meaningless and fragmented line segments. Then, a novel line segment descriptor with a new histogram binning strategy, which is robust to global geometrical distortions, is generated for each line segment based on the geometrical relationships,including both the locations and orientations of theremaining line segments relative to it. As a result of the invariance of the main shape contours, correct line segment matches will have similar descriptors and can be obtained by cross-matching among the descriptors. Finally, a spatial consistency measure is used to remove incorrect matches, and transformation parameters between the reference and sensed images can be figured out. Experiments with images from different types of satellite datasets, such as Landsat7, QuickBird, WorldView, and so on, demonstrate that the proposed algorithm is automatic, fast (4 ms faster than the second fastest method, i.e., the rotation-and scale-invariant shape context) and can achieve a recall of 79.7%, a precision of 89.1% and a root mean square error (RMSE) of 1.0 pixels on average for remote sensing images with large background variations.

Remote Sensing Image Registration with Line Segments and Their Intersections

“…In this section, the performance of the proposed RLI method is evaluated on a series of synthetic and real remote sensing image pairs, and then compared with the performances of RMLSM [31], SIFT [12], MSLD [25] and LP [29]. The parameter setting, data sets, and experimental results are presented as follows.…”

“…This algorithm can robustly match frontal faces under extreme illuminations; but the vertical symmetry of frontal faces which was used to remove false edges, might not be effective in other scenarios. Shi and Jiang [31] proposed an automatic image registration method that utilized the midpoints of line segments to generate shape context and describe shape contours (named RMLSM for short). The experimental results showed that this method could be used in the registration of remote sensing images with evident background changes.…”

Matching of Remote Sensing Images with Complex Background Variations via Siamese Convolutional Neural Network

“…To evaluate its performance, the complete framework is compared with SIFT and other three state-of-the-art matching methods, namely, two matching methods for remote sensing images with background variations (i.e., see Jiang [5] and Shi [20]) and a 2-channel deep network-based method (i.e., see Zagoruyko [19]). The comparative NCM, MP, and RMSE values are shown in Tables 2-4, respectively.…”

“…However, this method does not match with high-resolution remote sensing images because unreliable edge gradient information exists in these kinds of images. A line segment-based method is proposed to match remote sensing images with large background variations [20]. In this method, line segments are extracted by using an edge drawing line (EDLines [20]) detector.…”

“…A line segment-based method is proposed to match remote sensing images with large background variations [20]. In this method, line segments are extracted by using an edge drawing line (EDLines [20]) detector. Line validation is performed to obtain the main shape contour, and histogram binning shape-based descriptors are used to match the line segments.…”