High-resolution remote sensing image scene classifying method based on unsupervised feature learning

Abstract

A high-resolution remote sensing image scene classifying method based on unsupervised feature learning comprises the steps that original input high-resolution remote sensing images are divided to obtain scenes, a plurality of training image blocks are randomly extracted from each scene, and the training image blocks are gathered for conducting preprocessing operation; the low dimension manifold representation of all the training image blocks is calculated, and a set of clustering center is obtained by clustering; intensive sampling is conducted on each scene to obtain local image blocks, each local image block is subjected to preprocessing operation and then is mapped to the same low dimension manifold space, and then encoding is conducted to obtain all local features of the scenes; the local features of all the scenes are gathered to conduct feature quantization, the local feature column diagrams of all the scenes are counted to obtain the global feature representation of the scenes; a plurality of scenes are randomly selected to be used as training samples, the predicted class labels of all the scenes are obtained through a classifier, and thus the labeling task of the original high-resolution remote sensing scenes is achieved.

Description

technical field [0001] The invention belongs to the field of intelligent analysis of remote sensing images, in particular to scene classification for high-resolution remote sensing images, and is a remote sensing scene classification method based on non-supervised feature learning. Background technique [0002] With the rapid development of photogrammetry and remote sensing imaging technology, the number of high-resolution remote sensing images has also increased rapidly, and the demand for remote sensing image interpretation has become more and more urgent. The scene classification of remote sensing images is an important task in the field of intelligent remote sensing information processing, so the rapid understanding and automatic labeling of high-resolution remote sensing image scenes have also received more attention. [0003] A remote sensing scene usually refers to a local area with semantic information in a remote sensing image. For example, a remote sensing image of...

AI Technical Summary

Problems solved by technology

However, these algorithms directly use the original form of the data as the training data, and do not mine the intrinsic structure and information of the training data in the original data space, making it too computationally expensive in the training and encoding process

Images