Unsupervised learning scene feature rapid extraction method fusing semantic information

Abstract

The invention discloses an unsupervised learning scene feature rapid extraction method fusing semantic information, which belongs to the technical field of image processing. The method mainly solves the technical problem of image feature description in the scene recognition problem. In view of the problem of serious interference of unstable information in an image on a scene matching effect and the problem of poor robustness of binarization feature descriptors to severe environmental changes, accurate scene semantic features are extracted through a semantic segmentation model obtained througha weighted model fusion strategy to guide the detection of a key region containing specific information; on the basis of the region, a screening strategy based on pixel point position clues and an unsupervised learning algorithm are respectively adopted to extract a binarization feature descriptor with high discrimination capability, so that the scene matching precision can be improved while the calculation complexity is reduced.

Description

technical field [0001] The invention relates to the technical field of image processing, and relates to a fast extraction method of unsupervised learning scene features fused with semantic information. Background technique [0002] Scene feature extraction is often used to extract specific information in the scene so as to retrieve scenes with consistent content from the scene database. It has a wide range of applications in image retrieval, visual positioning, closed-loop detection and other fields. [0003] In the face of complex and changeable scenes, how to quickly extract stable features from them is a key technology in visual positioning tasks. Manually extracted features are widely used in visual localization systems, and can be divided into two categories according to the size of the feature description area: local features and global features. Methods based on local features, such as SIFT, SURF, ORB, describe the image by extracting feature points. This method only...

AI Technical Summary

Problems solved by technology

In order to solve the problem that the unstable information in the image seriously interferes with the scene matching effect and the problem that the binarized feature descriptor has insufficient discrimination for complex scenes, the present invention provides a fast extraction method for unsupervised learning scene features that fuses semantic information

Images