Remote sensing image scene classification method based on image transformation and BoF model

Abstract

The invention discloses a remote sensing image scene classification method based on image transformation and a BoF model, and the method comprises the steps of carrying out the partitioning processing of a remote sensing image, obtaining an image block set, carrying out the improved Radon transformation of all image block sets, carrying out the local feature extraction through combining the scale invariant feature transformation SIFT of the image block set, and obtaining a local fusion feature of the improved Radon transform feature and the SIFT feature; secondly, carrying out edge detection on the whole remote sensing image, and improving Radon transformation to obtain global features of the remote sensing image; then, using an improved m-RMR correlation analysis algorithm based on mutual information for carrying out feature optimization on the local fusion features and the global features, removing unfavorable and redundant features, clustering all the features to generate feature words, and using an improved PCA algorithm for carrying out weighted fusion on the feature words to obtain a fusion feature; obtaining a fusion feature word bag model of the local features and the global features; and finally, inputting a support vector machine (SVM) to generate a classifier and realizing remote sensing image scene classification.

Description

technical field [0001] The invention relates to image processing technology, in particular to a scene classification method for remote sensing images. Background technique [0002] Remote sensing image scene classification has always been an important application field of remote sensing images. Remote sensing image scene classification is widely used in natural disaster detection, land resource allocation and coverage management and other fields. How to extract effective image features from remote sensing images to represent remote sensing images has always been a core issue. [0003] Remote sensing image scene classification methods are mainly divided into three types: based on low-level visual features, based on middle-level visual features, and based on high-level visual features. Based on the underlying visual features, the spectrum, texture, and structural information of the sensory image are directly extracted as features, such as SIFT, LBP, GIST, HOG, etc.; based on ...

AI Technical Summary

Problems solved by technology

SIFT is easy to combine with other forms of feature vectors; it also has the advantages of rotation invariance, scale invariance, and insensitivity to brightness changes. It has better performance for remote sensing images with obvious texture features, but for remote sensing images with insignificant texture features Its effect is not ideal

Images