Adaptive two-stage feature point matching method based on matching difficulty

Abstract

The invention discloses an adaptive two-stage feature point matching method based on matching difficulty, and belongs to the technical field of image processing. According to the technical scheme of the invention, the method comprises the steps: firstly, selecting a subsequent specific matching mode based on the difference degree of pictures between picture pairs, and if the difference degree of the pictures is small, directly carrying out the matching processing based on the Euclidean distance between descriptors of feature points; otherwise, performing dimension raising processing on the position information of the feature point of each picture to enable the dimension of the feature point to be consistent with the dimension of the descriptor, adding the descriptor and the position information after the dimension raising processing to obtain a new descriptor of each feature point, and performing attention aggregation processing to obtain a matched descriptor of each feature point, and performing matching processing based on an inner product between the matching descriptors. The method is used for feature point matching of the image pair, adaptive two-stage feature point matching is realized, and matching accuracy and processing efficiency are improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an adaptive two-stage feature point matching method based on matching difficulty. Background technique [0002] Feature point matching refers to how to correctly match the feature point sets of different pictures after the feature point sets are extracted from the picture. It has important applications in geometry-based computer vision tasks. For example, simultaneous positioning and mapping technology is the key technology of unmanned driving. By extracting and matching feature points from the pictures captured by the camera, according to the matching relationship, the position information of the robot or vehicle at each moment can be calculated. A good matching result not only helps to improve the accuracy of the subsequent calculated position, but also provides a good initial value for the subsequent iterative algorithm, helping the iterative algorithm to...

AI Technical Summary

Problems solved by technology

But it is followed by an increase in the amount of calculations, which makes it difficult to apply feature point matching tasks to real-time applications, such as simultaneous positioning and mapping

Images