Spatiotemporal Fusion of Remote Sensing Image Based on Deep Learning

Xiaofei Wang,Xiaoyi Wang

doi:10.1155/2020/8873079

Abstract

High spatial and temporal resolution remote sensing data play an important role in monitoring the rapid change of the earth surface. However, there is an irreconcilable contradiction between the spatial and temporal resolutions of the remote sensing image acquired from a same sensor. The spatiotemporal fusion technology for remote sensing data is an effective way to solve the contradiction. In this paper, we will study the spatiotemporal fusion method based on the convolutional neural network, which can fuse the Landsat data with high spatial but low temporal resolution and MODIS data with low spatial but high temporal resolution, and generate time series data with high spatial resolution. In order to improve the accuracy of spatiotemporal fusion, a residual convolution neural network is proposed. MODIS image is used as the input to predict the residual image between MODIS and Landsat, and the sum of the predicted residual image and MODIS data is used as the predicted Landsat-like image. In this paper, the residual network not only increases the depth of the superresolution network but also avoids the problem of vanishing gradient due to the deep network structure. The experimental results show that the prediction accuracy by our method is greater than that of several mainstream methods.

Highlights

Due to the limitation of the hardware technology of the remote sensing satellite and the cost of satellite launching, it is difficult for the same satellite to obtain the remote sensing image with both high spatial and temporal resolutions
We introduce the idea of ResNet [28] and set up a spatiotemporal fusion framework of remote sensing image suitable for a small-sample training set for convolutional neural network (CNN)
If we want to learn such a model, the training difficulty will be greater; if we have learned the more saturated accuracy, the learning goal will be transformed into the learning of identity mapping, that is, to make the input x an approximate output HðxÞ, which is in order to keep in the later hierarchy without causing a drop in accuracy

Summary

Introduction

Due to the limitation of the hardware technology of the remote sensing satellite and the cost of satellite launching, it is difficult for the same satellite to obtain the remote sensing image with both high spatial and temporal resolutions. Landsat series satellites can obtain multispectral data with a spatial resolution of 30 m. Multispectral image imaging is more convenient, making it widely used in many fields With this feature, Landsat data has been widely used in the exploration of earth resources, management of agriculture, forestry, animal husbandry, and natural disaster and environmental pollution monitoring [2,3,4]. The 16day visit circle of the Landsat satellite and the impact of cloud pollution limit their potential use in monitoring and researching the land surface dynamic changes. Moderate-resolution Imaging Spectroradiometer (MODIS) on Terra/Aqua satellite has a visit circle per 1-2 days, which has a high temporal resolution and can be applied in vegetation phenology [5, 6] and other fields. The spatial resolution of MODIS data is 250-1000 m, which has a poor representation of the details of the ground objects and is not enough to observe the heterogeneous landscape

Objectives

Methods

Findings

Conclusion