计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (5): 161-169.doi: 10.11896/jsjkx.220300110

• 计算机图形学&多媒体 • 上一篇    下一篇

基于MLUM-Net的高分遥感影像土地利用多分类方法

胡绍凯1, 赫晓慧2, 田智慧2   

  1. 1 郑州大学信息工程学院 郑州 450001
    2 郑州大学地球科学与技术学院 郑州 450052
  • 收稿日期:2022-03-10 修回日期:2022-04-29 出版日期:2023-05-15 发布日期:2023-05-06
  • 通讯作者: 赫晓慧(hexh@zzu.edu.cn)
  • 作者简介:(18538256320@163.com)
  • 基金资助:
    河南省重大科技专项(201400210900);第二次青藏高原综合科学考察研究项目(2019QZKK0106)

Land Use Multi-classification Method of High Resolution Remote Sensing Images Based on MLUM-Net

HU Shaokai1, HE Xiaohui2, TIAN Zhihui2   

  1. 1 School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China
    2 School of Earth Science and Technology,Zhengzhou University,Zhengzhou 450052,China
  • Received:2022-03-10 Revised:2022-04-29 Online:2023-05-15 Published:2023-05-06
  • About author:HU Shaokai,born in 1995,postgra-duate.His main research interests include artificial intelligence,remote sensing image processing.
    HE Xiaohui,born in 1978,Ph.D,professor.Her main research interests include artificial intelligence,computer vision,remote sensing image processing,and data mining.
  • Supported by:
    Key Technologies for the Construction and Service in Henan Province(201400210900) and Second Tibetan Pla-teau Scientific Expedition and Research(STEP) Program(2019QZKK0106).

PDF (PC)

323

摘要： 针对高分辨率遥感影像土地利用多分类结果中地块结构不完整、边界质量差的问题,提出了基于MLUM-Net模型的遥感影像土地利用多分类方法。该方法利用多尺度空洞卷积和通道注意力机制构造MDSPA编码器,提高了网络多尺度特征提取能力与地块位置定位的准确性,并通过空间注意力机制自适应增强了多尺度特征表达;为消除上采样语义损失和减少分类结果噪声,设计了混合池化上采样优化模块,用于优化分类结果并消除网络分类误差;根据土地利用多分类数据集类别占比不均衡的特点和地块结构的相似性指数设计混合损失函数,消除数据类别占比产生的影响,提高地块结构完整性和精细化分类边界。在多个数据集上进行了实验验证,总体精度和kappa指标均有明显提高,其分类结果结构完整且边缘划分准确,在土地利用多分类领域具有较好的实用价值。

关键词: 遥感影像, 土地利用分类, MLUM-Net, 注意力机制, 多尺度特征

Abstract: Aiming at the problems of incomplete land plot structure and poor boundary quality in high-resolution remote sensing image land use multi-classification,a multi-classification method of remote sensing image land use based on MLUM-Net model is proposed.This method uses the multi-scale hole convolution and channel attention mechanism to construct the MDSPA encoder,which improves the network multi-scale feature extraction ability and the accuracy of the parcel's location and adaptively enhances the multi-scale feature expression through the spatial attention mechanism.To eliminate the semantic loss of upsampling and reduce the noise of classification results,a hybrid pooling upsampling optimization module is designed to optimize the classification results and eliminate the network classification errors.According to the characteristics of unbalanced classification ratio of multi-classification data set of land use and the similarity index of plot structure,this paper designs a mixed loss function to eliminate the influence of data category ratio.This function improves the structural integrity of the block and refines the classification boundary.Experimental verification has been carried out on multiple data sets,and the overall accuracy and kappa index have been significantly improved.The classification result has a complete structure and accurate edge division,which has good practical value in the land use multi-classification.

Key words: Remote sensing image, Land use classification, MLUM-UNet, Attention mechanism, Multi-scale features

中图分类号: 

  • TP391.4
[1]SU M,GUO R Z,CHEN B,et al.Sampling Strategy for Detailed Urban Land Use Classification:A Systematic Analysis in Shen-zhen[J].Remote Sensing,2020,12(9):1497.
[2]MEN J L,LIU Y Y,ZHANG B.High-scoring Image Land Use Classification Based on Feature Cascades of Multi-Structure Convolutional Neural Network[J].Geomatics and Information Science of Wuhan University,2019,44(12):1841-1848.
[3]CHEN K Q,ZHU Z L,DENG X P,et al.Deep Learning forMulti-scale Object Detection:A Survey[J].Journal of Software,2021,32(4):1201-1227.
[4]FENG F,LIU P X,LI L,et al.Study of FCM Fusing Improved Gravitational Search Algorithm in Medical Image Segmentation[J].Computer Science,2018,45(S1):252-254.
[5]MARCOS D,VOLPI M,KELLENBERGER B,et al.Land covermapping at very high resolution with rotation equivariant CNNs Towards small yet accurate models[J].Isprs Journal of Photogrammetry & Remote Sensing,2018,145PA(NOV.):96-107.
[6]MEMON N,PARIKH H,PATEL D,et al.Automatic LandCover Classification of Multi-Resolution Dualpol Data using Convolutional Neural Network(CNN)[J].Remote Sensing Applications Society and Environment,2021(2):100491.
[7]XIA M,CAO G,WANG G Y,et al.Remote Sensing Image Classification Based on Deep Learning and Conditional Random Fields[J].Journal of Image and Graphics,2017,22(9):1289-1301.
[8]YAO X,YANG H,WU Y,et al.Land Use Classification of the Deep Convolutional Neural Network Method Reducing the Loss of Spatial Features[J].Sensors,2019,19(12):2792-2807.
[9]CHAI H B,YAN C,ZOU Y F,et al.Using PSP Net to Realize Land Cover Classification of Remote Sensing Imagery in Hubei Province[J].Geomatics and Information Science of Wuhan University,2021,46(8):1224-1232.
[10]MENG Q X,DUAN X L.High-resolution Remote SensingImage Scene Classification Based on DCNN[J].Journal of Central China Normal University(Natural Sciences),2019,53(4):568-574.
[11]ZHANG W,TANG P,ZHAO L.Fast and accurate land cover classification on medium resolution remote sensing images using segmentation models[J].International Journal of Remote Sen-sing,2021,42(9):3277-3301.
[12]YANG M,YU K,CHI Z,et al.DenseASPP for semantic segmentation in street scenes[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.2018:3684-3692.
[13]HUANG G,LIU Z,LAURENS V D M,et al.Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2017:2261-2269.
[14]AIHICHRE H,ALSUWAYED A,BAZI Y,et al.Classification of Remote Sensing Images using EfficientNet-B3 CNN Model with Attention[J].IEEE Access,2021,9(9):14078-14094.
[15]RONNERBERGER O,FISCHERF P,BROX T.U-Net:Convolutional Networks for Biomedical Image Segmentation[J].Medical Image Computing and Computer Assisted Intervention,2015,28(4):234-241.
[16]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection[C]//IEEE International Conference on Computer Vision(ICCV).2017:2999-3007.
[17]WANG Z,BOVIK A C,SHEIKH H R,et al.Image Quality Assessment:From Error Visibility to Structural Similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[18]ROBINSON C,HOU L,MALKIN K,et al.Large Scale High-Resolution Land Cover Mapping with Multi-Resolution Data[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2019.
[19]TONG X Y,XIA G S,LU Q,et al.Land-cover classificationwith high-resolution remote sensing images using transferable deep models[J].Remote Sensing of Environment,2020,237:111322.
[20]CHAURASIA A,CULURCIELLO E.Exploiting encoder representations for efficient semantic segmentation[C]//2017 IEEE Visual Communications and Image Processing(VCIP).2017:1-4.
[21]YANG M,YU K,ZHANG Z,et al.DenseASPP for Semantic Segmentation in Street Scenes[C]//2018 IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.2018:3684-3692.
[22]CHEN L C,PAPANDREOU G,SCHROFFF,et al.Rethinking Atrous Convolution for Semantic Image Segmentation[C]//Computer Vision and Pattern Recognition.2017.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发