High-resolution remote sensing image impervious surface extraction method and system based on deep learning and semantic probability

Abstract

A high-resolution remote sensing image impervious surface extraction method and system based on deep learning and semantic probability. The method includes: obtaining a high-resolution remote sensingimage of a target region, normalizing image data, dividing the image data into a sample image and a test image; constructing a deep convolutional network, wherein the deep convolutional network is composed of a multi-layer convolution layer, a pooling layer and a corresponding deconvolution and deconvolution layer, and extracting image features of each sample image; predicting each sample image pixel by pixel, and constructing a loss function by using the error between the predicted value and the true value, and updating and training the network parameters; extracting the test image features by the deep convolutional network, and carrying out the pixel-by-pixel classification prediction, then constructing a conditional random field model of the test image by using the semantic associationinformation between pixel points, optimizing the test image prediction results globally, and obtaining the extraction results. The invention can accurately and automatically extract the impervious surface of the remote sensing image, and meets the practical application requirements of urban planning.

Description

technical field [0001] The invention belongs to the field of information extraction of remote sensing image data, and relates to a technical scheme for extracting impermeable surfaces of high-resolution remote sensing images combined with deep learning and semantic probability. Background technique [0002] Impervious Surface refers to the artificial surface on the ground that prevents water from penetrating into the soil. Common examples include buildings, roads, squares, parking lots, etc. It is one of the key indicators for evaluating the health of urban ecosystems and the quality of human settlements. Deep learning, especially the convolutional neural network, by simulating the cognitive process of the human brain, extracts and recognizes features from low-level to high-level external input signals, and has achieved a lot in the fields of natural image classification, segmentation and content understanding. A series of breakthrough application results. However, for remo...

AI Technical Summary

Problems solved by technology

However, for remote sensing images with lower spatial resolution and more complex object types, it is difficult for convolutional neural networks to effectively establish the spatial relationship between different objects, resulting in fragmented or unreasonable classification results.

Images