Dual-channel convolutional neural network for change detection of multitemporal SAR images

Tao Liu, Ying Li, Longhao Xu

科研成果: 书/报告/会议事项章节会议稿件同行评审

6 引用 (Scopus)

摘要

This paper presents a new dual-channel convolutional neural network (CNN) which is designed to SAR image change detection to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN structures, which can extract features from two multitemporal SAR images. Experimental evaluation on simulated datasets and real SAR images from different satellites shows a satisfying performance of the proposed model. It is the second-place winner when detecting the simulated images with Gamma noise, but it wins the top place when detecting the real flood images.

源语言英语
主期刊名2016 International Conference on Orange Technologies, ICOT 2016
出版商Institute of Electrical and Electronics Engineers Inc.
60-63
页数4
ISBN(电子版)9781538648315
DOI
出版状态已出版 - 2 7月 2016
活动2016 International Conference on Orange Technologies, ICOT 2016 - Melbourne, 澳大利亚
期限: 18 12月 201620 12月 2016

出版系列

姓名2016 International Conference on Orange Technologies, ICOT 2016
2018-January

会议

会议2016 International Conference on Orange Technologies, ICOT 2016
国家/地区澳大利亚
Melbourne
时期18/12/1620/12/16

指纹

探究 'Dual-channel convolutional neural network for change detection of multitemporal SAR images' 的科研主题。它们共同构成独一无二的指纹。

引用此