中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images

文献类型：期刊论文

作者Li, Lianfa1,2
刊名REMOTE SENSING
出版日期2019-09-01
卷号11期号:18页码:24
关键词residual learning autoencoder multiscale atrous spatial pyramid pooling semantic segmentation remotely sensed land-use images
DOI10.3390/rs11182142
通讯作者Li, Lianfa(lilf@lreis.ac.cn)
英文摘要Semantic segmentation is a fundamental means of extracting information from remotely sensed images at the pixel level. Deep learning has enabled considerable improvements in efficiency and accuracy of semantic segmentation of general images. Typical models range from benchmarks such as fully convolutional networks, U-Net, Micro-Net, and dilated residual networks to the more recently developed DeepLab 3+. However, many of these models were originally developed for segmentation of general or medical images and videos, and are not directly relevant to remotely sensed images. The studies of deep learning for semantic segmentation of remotely sensed images are limited. This paper presents a novel flexible autoencoder-based architecture of deep learning that makes extensive use of residual learning and multiscaling for robust semantic segmentation of remotely sensed land-use images. In this architecture, a deep residual autoencoder is generalized to a fully convolutional network in which residual connections are implemented within and between all encoding and decoding layers. Compared with the concatenated shortcuts in U-Net, these residual connections reduce the number of trainable parameters and improve the learning efficiency by enabling extensive backpropagation of errors. In addition, resizing or atrous spatial pyramid pooling (ASPP) can be leveraged to capture multiscale information from the input images to enhance the robustness to scale variations. The residual learning and multiscaling strategies improve the trained model's generalizability, as demonstrated in the semantic segmentation of land-use types in two real-world datasets of remotely sensed images. Compared with U-Net, the proposed method improves the Jaccard index (JI) or the mean intersection over union (MIoU) by 4-11% in the training phase and by 3-9% in the validation and testing phases. With its flexible deep learning architecture, the proposed approach can be easily applied for and transferred to semantic segmentation of land-use variables and other surface variables of remotely sensed images.
资助项目Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19040501] ; National Natural Science Foundation of China[41471376]
WOS研究方向Remote Sensing
语种英语
WOS记录号WOS:000489101500072
出版者MDPI
资助机构Strategic Priority Research Program of the Chinese Academy of Sciences ; National Natural Science Foundation of China
源URL[http://ir.igsnrr.ac.cn/handle/311030/129728]  
专题中国科学院地理科学与资源研究所
通讯作者Li, Lianfa
作者单位1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Datun Rd, Beijing 100101, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Li, Lianfa. Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images[J]. REMOTE SENSING,2019,11(18):24.
APA Li, Lianfa.(2019).Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images.REMOTE SENSING,11(18),24.
MLA Li, Lianfa."Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images".REMOTE SENSING 11.18(2019):24.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。