Abstract
Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective.
Highlights
Remote sensing technology has the advantages of a large detection range, fast data acquisition, and few restricted conditions [1,2,3]
The edge matching rate (EMR) is the ratio of edge points to matching edge points in another image, and it is calculated by Equation (6)
According to the analysis of the above results, edge and texture locations with rich edge points contain the main information of an image, so edge matching can determine the matching effect of the entire image
Summary
Remote sensing technology has the advantages of a large detection range, fast data acquisition, and few restricted conditions [1,2,3]. The most commonly used method for the 3D reconstruction of satellite remote sensing images is to obtain the disparity map of the image pair using stereo matching, and the real geographic coordinates and elevation are calculated using the rational function model [7,8,9,10,11,12,13]. Traditional stereo matching methods usually utilize the low-level features of image patches around the pixel to measure the dissimilarity. Local descriptors, such as absolute difference (AD), the sum of squared difference (SSD), census transform [14], or their combination (AD-CENSUS) [15], are often employed. For cost aggregation and disparity optimization, some global methods treat disparity selection as a multi-label learning problem and optimize a corresponding
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
