The Method of Extracting Land Classification Information by HRI-RefineNET Model

Hao Fan,De-Qin Shu,Qingdi Wei

doi:10.1109/access.2019.2960817

Abstract

Accurate land use classification results play an important role in scientific research and production practice. The existing neural network structure contains many pooling layers. Although the model incorporated spatial location information when extracting ground object information, many detailed features were also lost. At the same time, due to the great difference between remote sensing image and natural image, the model with good performance of natural image extraction cannot be transplanted directly into the extraction of high-resolution remote sensing image. Based on RefineNET model, this paper proposes an improved HRI-RefineNet (High Resolution Image) model. The model chooses farmland, residential areas, forest, roads and water area as extraction targets, and establishes a new method for extracting land classification information from high resolution remote sensing images. The proposed HRI-RefineNet model adjust the convolution layer number and convolution kernel size respectively according to the texture features of different five kinds of ground objects. An improved pooling layer is designed for the HRI-RefineNet for reducing the loss of location information in feature maps. A decoder group is added to the HRI-RefineNet model. 29 remote sensing images of Tai'an city, China, from 2015 to 2017 were selected for experiment. The experimental results showed that the accuracy of farmland, residential areas, forest, roads and water area obtained by HRI-RefineNET model was 93.9%, 92.3%, 91.7%, 90.1%, 88.7%, respectively, superior to the RefineNET model and some existing advanced models.

Highlights

Land use classification plays an important role in the adjustment of land use structure, rational exploitation of land resources and dynamic monitoring of land use status [1], [2]
Because the features of different types of ground objects in high resolution remote sensing image are different, too many convolution and pooling layers cannot adapt to the extraction of features of various types of objects
1) The number of convolution layers and the size of convolution kernel in HRI-RefineNet model is adjusted according to the features of different ground objects

Summary

Introduction

Land use classification plays an important role in the adjustment of land use structure, rational exploitation of land resources and dynamic monitoring of land use status [1], [2]. Because the features of different types of ground objects (e.g., farmland, residential areas, forest, roads and water area) in high resolution remote sensing image are different, too many convolution and pooling layers cannot adapt to the extraction of features of various types of objects.

Results

Conclusion