Large viewing angle image matching method capable of combining region matching and point matching

Abstract

The invention relates to a large viewing angle image matching method capable of combining region matching and point matching. The method comprises the steps of 1, inputting two images having large viewing angle changes; 2, carrying out region detection on the images by a maximally stable extremal region (MSER), and fitting an elliptic region by the mean value and the variance of the region; 3, normalizing the elliptic region into a circular region, and describing the circular region by a scale invariant feature transform (SIFT) descriptor; 4, adopting the nearest-neighbor than the next-nearest neighbor strategy, and selecting the initial region matching pair; 5, in the region matching pair, detecting feature points by an SIFT method; 6, describing the feature points to obtain an MSER-based 128-dimensional descriptor and a 2-dimensional space descriptor; 7, adopting a similarity strategy combined with the distance, and selecting an accurate matching point pair in the two images. The large viewing angle image matching method overcomes the defect that in the prior art, the description of the feature points does not have affine invariant and leaves out of consideration of space information, and can extract the matching point pair with higher accuracy so as to enable the matching point pair to be better used for image registration.

Description

technical field [0001] The present invention belongs to the technical field of image processing, and further relates to a large-view image matching method combining region matching and point matching in the technical field of image registration. The present invention can more accurately extract consistent feature points from input images, and can be applied to image registration with large viewing angles. Background technique [0002] Image matching is a special field of image processing. Through image matching, consistent feature points are extracted between different images of the same scene to determine the corresponding geometric relationship between images and obtain a matched image. The matched image can more accurately describe the image scene than a single image. In general, image matching can be performed using methods based on local feature extraction and matching. These local feature extraction and matching methods mainly consider the scale and Rotation invarianc...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that because the method simulates the image in the affine space to form images from various perspectives, it consumes a lot of memory; at the same time, it also introduces a large number of wrong matching points when extracting a large number of correct matching points. , resulting in a decrease in the correct matching rate

Images