Abstract
Abstract. With the rapid development of subpixel matching algorithms, the estimation of image shifts with an accuracy of higher than 0.05 pixels is achieved, which makes the narrow baseline stereovision possible. Based on the subpixel matching algorithm using the robust phase correlation (PC), in this work, we present a novel hierarchical and adaptive disparity estimation scheme for narrow baseline stereo, which consists of three main steps: image coregistration, pixel-level disparity estimation, and subpixel refinement. The Fourier-Mellin transform with subpixel PC is used to co-register two input images. Then, the pixel-level disparities are estimated in an iterative manner, which is achieved through multiscale superpixels. The pixel-level PC is performed with the window sizes and locations adaptively determined according to superpixels, with the disparity values calcualted. Fast weighted median filtering based on edge-aware filter is adopted to refine the disparity results. At last, the accurate disparities are calculated via a robust subpixel PC method. The combination of multiscale superpixel hierarchy, adaptive determination of the window size and location of correlation, fast weighted median filtering and subpixel PC make the proposed scheme be able to overcome the issues of either low-texture areas or fattening effect. Experimental results on a pair of UAV images and the comparison with the fixed-window PC methods, the iterative scheme with fixed variation strategy, and a sophisticated implementation using global optimization demonstrate the superiority and reliability of the proposed scheme.
Highlights
Recovering the depth from stereo imagery is one of the cricual problems in photogrammetry
While in the work of (Li et al, 2016), a hierarchical and adaptive framework is developed for the disparity estimation of unmanned aerial vehicle (UAV) images, with a fixed variation strategy of window sizes and step size
The pixel-level disparities are estimated in an iterative manner, which is achieved through multiscale superpixels
Summary
Recovering the depth from stereo imagery is one of the cricual problems in photogrammetry. In the urban area, tall man-made infrastructures (e.g., skyscrapers or TV tower) will occlude lower neighboring objects (Xu et al, 2013), which will generate occlusions and shadows in the stereo images, making the matching of images more difficult To tackle those problems, the stereovision constructed by a narrow baseline could be one of the alternatives (Delon , Rouge, 2007). When the correlation window strides across the depth discontinuities, the matching process suffers from the fattening effect that object boundaries are not reconstructed correctly In this case, in addition to the subpixel matching algorithm, an effective matching scheme is indispensable for narrow baseline stereo. While in the work of (Li et al, 2016), a hierarchical and adaptive framework is developed for the disparity estimation of UAV images, with a fixed variation strategy of window sizes and step size.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
