跳到主要导航 跳到搜索 跳到主要内容

Classification of fusing SAR and multispectral image via deep bimodal autoencoders

  • Jie Geng
  • , Hongyu Wang
  • , Jianchao Fan
  • , Xiaorui Ma
  • Dalian University of Technology
  • National Marine Environmental Monitoring Center

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

9 引用 (Scopus)

摘要

Classification of multisensor data provides potential advantages over a single sensor in accuracy. In this paper, deep bimodal autoencoders are proposed for classification of fusing synthetic aperture radar (SAR) and multispectral images. The proposed deep network based on autoencoders is trained to discover both independencies of each modality and correlations across the modalities. Specifically, the sparse encoding layers in the front are applied to learn features of each modality, then shared representation layers in the middle are developed to learn fused features of two modalities, finally softmax classifier in the top is adopted for classification. Experimental results demonstrate that the proposed network is able to yield superior classification performance compared with some related networks.

源语言英语
主期刊名2017 IEEE International Geoscience and Remote Sensing Symposium
主期刊副标题International Cooperation for Global Awareness, IGARSS 2017 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
页823-826
页数4
ISBN(电子版)9781509049516
DOI
出版状态已出版 - 1 12月 2017
已对外发布是
活动37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017 - Fort Worth, 美国
期限: 23 7月 2017 → 28 7月 2017

丛书

姓名International Geoscience and Remote Sensing Symposium (IGARSS)
卷2017-July
ISSN(电子版)2153-7003

会议

会议37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017
国家/地区美国
市Fort Worth
时期23/07/17 → 28/07/17

学术指纹

探究 'Classification of fusing SAR and multispectral image via deep bimodal autoencoders' 的科研主题。它们共同构成独一无二的学术指纹。

引用此