Remote sensing image classification method based on multi-scale depth features

Abstract

The invention belongs to the technical field of remote sensing image classification, and particularly relates to a remote sensing image classification method based on multi-scale depth features. Firstly, the algorithm can automatically establish multi-scale image pyramid; secondly, by means of a traditional convolutional neural network algorithm, the algorithm can automatically extract high-levelimage features by means of a self-learning algorithm; and finally, the multi-scale depth image features are fused with the spectral features, thereby improving the remote sensing image classificationprecision. According to the multi-scale deep neural network algorithm, a multi-scale image pyramid can be automatically constructed for an input remote sensing image, and then a multi-scale training sample is extracted and used for extracting multi-scale image spatial features. The algorithm has the following two advantages: 1) deep stable and effective image features can be automatically extracted, and 2) the multi-scale feature learning method can effectively describe the multi-scale effect of a complex ground object target in an image.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image classification, and in particular relates to a remote sensing image classification method based on multi-scale depth features. Background technique [0002] The emergence and development of remote sensing technology as a data acquisition method that can quickly obtain the real situation of a large area of ​​the ground without directly contacting the ground target reflects the improvement of human beings' ability to perceive geographical space and the earth's environment. Land cover and land surface information are the most direct environmental information in remote sensing images, and they are also the basic data of other environmental elements. It is noted that remote sensing data has the characteristics of large description range, dynamic acquisition, and fast update speed. Therefore, it can be widely used in various fields of social development and national economy, which shows the...

AI Technical Summary

Problems solved by technology

Note that traditional remote sensing image features are usually defined by human experience and there is a large degree of linear correlation and redundancy

Although in recent years, scholars have automatically selected effective features for ground objects from the feature database, due to the high complexity of high-resolution remote sensing images, shallow features (Gabor, EMPs, etc.) Object

Images