A Classification Method for High Resolution Remote Sensing Images Based on Feature Pooling and Denormalization Representation

Abstract

A remote sensing image classification method based on feature pooling and denormalization. Firstly, the remote sensing image is linearly filtered, and the features of the linear filtering results are combined by feature pooling, and then the high First-order correlation, extracting local descriptors in a dense grid manner, and finally performing feature encoding after Hellinger kernel mapping and feature dimensionality reduction to form a global expression of remote sensing images, and then completing the classification of remote sensing images after training and prediction, the present invention can Obtain high image classification accuracy, eliminate the redundancy of low-order and high-order statistical correlation in the image, enhance the invariance of target position, compact feature compression, reduce feature dimension, improve computational efficiency, and obtain better classification performance , easy to implement and high precision.

Description

technical field [0001] The invention relates to a technology in the field of remote sensing image processing, in particular to a remote sensing image classification method based on feature pooling and denormalization. Background technique [0002] A key step in the classification of high-resolution remote sensing images is to extract appropriate image features, and widely used features include texture features and local features. Common texture features include Gabor texture and LBP texture, and local features include HOG features, SIFT features, and Dense SIFT features. However, there are problems in image classification such as target scale, inconsistent illumination, target occlusion, and low-order and high-order correlation. [0003] Most of the existing visual vocabulary-based remote sensing image object classification methods are based on Gaussian blur and sampling to generate a multi-layer Gaussian space pyramid; then through SIFT feature extraction and LBP feature e...

AI Technical Summary

Problems solved by technology

However, image classification methods based on visual vocabulary are essentially limited by the shortcomings of the bag-of-words model.

First, the way of using frequency histogram features is not the optimal image representation

Second, the quantization of low-level descriptors (such as SIFT features) by the bag-of-words model is a lossy process

However, the convolutional neural network in this type of technology contains feature extraction of many convolutional layers, and each layer involves the convolution operation of a large number of filter cores. When further considering the combination of multiple convolutional neural networks , as the number of combinations increases, its computational complexity will increase exponentially

Images