Narrow Baseline Disparity Reconstruction Method Based on Multiscale Superpixels and Phase Correlation

Abstract

The present invention relates to a reconstruction method of narrow baseline disparity based on multi-scale superpixels and phase correlation. The method includes the following sub-steps: Step 1: Obtaining the global similarity between two input images by Fourier-Mellin transform method Transform the model; step 2: use the multi-scale superpixel method to estimate the pixel extreme error of the global similar transformation model, and obtain the pixel extreme error estimation result; step 3: use the method based on singular value decomposition and random sampling consistency for the pixel extreme error estimation result The sub-pixel phase correlation method performs sub-pixel precision acquisition operation and further obtains the final narrow baseline disparity result; Step 4: reconstructs the 3D information of the image according to the final narrow baseline disparity result. Compared with the prior art, the present invention has the advantages of high precision, good robustness, and high matching efficiency in low-texture regions.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a reconstruction method of narrow baseline stereo disparity based on multi-scale superpixels and phases. Background technique [0002] Recovering depth from stereo images is one of the key problems in photogrammetry and even computer vision. In traditional earth observation systems, in order to estimate the height of the ground, one or more pairs of stereo images obtained by satellites or aircrafts with wide photogrammetric baselines are usually used, and the base-to-height ratio (B / H ) in the range of 0.6-1.0. Theoretically, a large B / H ratio is required for stereo matching to ensure the accuracy of forward intersection in elevation estimation. However, for a pair of stereo images with a wide baseline, it means that the two images are acquired from completely different perspectives. In this case, during imaging, 3D objects are recorded on 2D image planes with differen...

AI Technical Summary

Problems solved by technology

On the other hand, in order to make the estimated disparity accurate enough, the following two main challenges need to be addressed: (1) Low-textured regions provide less matching information and make sub-pixel estimation unreliable, especially at small window sizes the case

(2) When the correlation window spans depth discontinuities, the matching process suffers from the fattening effect of not correctly reconstructing object boundaries

Images