A method for stitching aerial maps based on superpixel SIFT

Abstract

The invention discloses a method for aerial photography map splicing based on super-pixels and SIFT. The method comprises the steps that (1) super-pixel self-adaptation segmentation is conducted on aerial photography maps; (2) three to ten super-pixel pre-matching pairs are obtained by using the color normalization average value of a plurality of super-pixels obtained in the step (1) as guidance information, SIFT features of the super-pixel pre-matching pairs are extracted, and the super-pixel pre-matching pairs which fail in matching are removed after matching of the SIFT features is conducted; (3) a supervisory mechanism is generated in an on-line mode, and matching point pairs meeting the requirements are obtained; (4) a transformation matrix is calculated through the matching point pairs which are accurately selected in the step (3), images are fused, and image splicing is achieved. The method for aerial photography map splicing based on the super-pixels and SIFT achieves rapid and efficient splicing of the aerial photography maps, and the effectiveness of the method is verified through experiments.

Description

technical field [0001] The invention relates to the fields of geographical remote sensing and image processing, in particular to a method for splicing aerial maps based on superpixel SIFT. Background technique [0002] Aerial maps are captured by drones at high altitudes using high-altitude cameras. Due to the limitation of the flying height of the UAV and the focal length of the camera, it is difficult for a single aerial map to contain all the content of the target. Therefore, aerial map stitching has become a key issue in aerial map processing. [0003] Image mosaic technology is to combine several images with overlapping content into one image with a large viewing angle and wide format. This technology has been developed rapidly as a tool for synthesizing aerial maps. The key technology of image mosaic is registration, which needs to calculate the projective transformation between images according to the consistency of overlapping areas between images. [0004] Method...

AI Technical Summary

Problems solved by technology

In addition, aerial maps usually have the characteristics of high resolution and rich similar structures. The former results in a long time-consuming image registration based on SIFT features, and the latter, because SIFT features carry local neighborhood information, makes it relatively similar to locally similar features. Points are prone to mis-matching, so further screening of the extracted matching points is required

When the proportion of exactly matching point pairs is small, the RANSAC algorithm [4] The use of will further reduce splicing efficiency

Images