Remote sensing image classification method and device

Abstract

The invention provides a remote sensing image classification method and device. The method comprises the following steps: acquiring a to-be-classified image object; and inputting the to-be-classified image object into a classification model to obtain a classification result output by the classification model, wherein the classification model is obtained by training based on object features and depth features of sample image objects and category labels of the sample image objects. According to the invention, a good model training effect can be obtained by training the classification model based on the object features representing image shapes, spaces and other features of the sample image objects and the depth features of deep learning, so that the classification result of the to-be-classified image object can be better obtained, rapid and accurate classification of remote sensing images is realized, and the invention can be applied to land coverage / utilization mapping based on the remote sensing images.

Description

Technical field [0001] The present invention relates to the field of remote sensing imaging processing, and more particularly to a remote sensing imaging classification method and apparatus. Background technique [0002] The remote sensing image classification method has experienced a pixel-based image classification method to the object-oriented image classification method to a deep learning-based image classification method. The pixel-based image classification method is mainly to classify the remote sensing images with lower spatial resolution early in the early remote sensing development. With the increase in remote sensing image spatial resolution, the heterogeneity of the object, the heterogeneity and interval similarity of the ground object is increasing, and the object-oriented image classification method is more suitable for this. Subsequently, the rise of deep learning has also been developed in many deep learning-based remote sensing classification methods. [0003] Ob...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a remote sensing image classification method and device, which are used to solve the defect that the object-oriented image classification method and the deep learning-based image classification method cannot be fully combined and applied in the prior art, and realize the object-oriented image classification method and the depth-based image classification method. Learned image classification methods are effectively combined with

Images