A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images
Information extraction from multi-sensor remote sensing images has increasingly attracted attention with the development of remote sensing sensors. In this study, a supervised change detection method, based on the deep Siamese convolutional network with hybrid convolutional feature extraction module...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/2/205 |
id |
doaj-abcc4d489d0b46d39b8a2404f9f51881 |
---|---|
record_format |
Article |
spelling |
doaj-abcc4d489d0b46d39b8a2404f9f518812020-11-25T00:30:22ZengMDPI AGRemote Sensing2072-42922020-01-0112220510.3390/rs12020205rs12020205A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing ImagesMoyang Wang0Kun Tan1Xiuping Jia2Xue Wang3Yu Chen4NASG Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaNASG Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Engineering and Information Technology, The University of New South Wales, Canberra, ACT 2600, AustraliaNASG Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaNASG Key Laboratory of Land Environment and Disaster Monitoring, China University of Mining and Technology, Xuzhou 221116, ChinaInformation extraction from multi-sensor remote sensing images has increasingly attracted attention with the development of remote sensing sensors. In this study, a supervised change detection method, based on the deep Siamese convolutional network with hybrid convolutional feature extraction module (OB-DSCNH), has been proposed using multi-sensor images. The proposed architecture, which is based on dilated convolution, can extract the deep change features effectively, and the character of “network in network” increases the depth and width of the network while keeping the computational budget constant. The change decision model is utilized to detect changes through the difference of extracted features. Finally, a change detection map is obtained via an uncertainty analysis, which combines the multi-resolution segmentation, with the output from the Siamese network. To validate the effectiveness of the proposed approach, we conducted experiments on multispectral images collected by the ZY-3 and GF-2 satellites. Experimental results demonstrate that our proposed method achieves comparable and better performance than mainstream methods in multi-sensor images change detection.https://www.mdpi.com/2072-4292/12/2/205multi-sensor imagechange detectionsiamese neural networkdilated convolutionobject-based image analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Moyang Wang Kun Tan Xiuping Jia Xue Wang Yu Chen |
spellingShingle |
Moyang Wang Kun Tan Xiuping Jia Xue Wang Yu Chen A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images Remote Sensing multi-sensor image change detection siamese neural network dilated convolution object-based image analysis |
author_facet |
Moyang Wang Kun Tan Xiuping Jia Xue Wang Yu Chen |
author_sort |
Moyang Wang |
title |
A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images |
title_short |
A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images |
title_full |
A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images |
title_fullStr |
A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images |
title_full_unstemmed |
A Deep Siamese Network with Hybrid Convolutional Feature Extraction Module for Change Detection Based on Multi-sensor Remote Sensing Images |
title_sort |
deep siamese network with hybrid convolutional feature extraction module for change detection based on multi-sensor remote sensing images |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-01-01 |
description |
Information extraction from multi-sensor remote sensing images has increasingly attracted attention with the development of remote sensing sensors. In this study, a supervised change detection method, based on the deep Siamese convolutional network with hybrid convolutional feature extraction module (OB-DSCNH), has been proposed using multi-sensor images. The proposed architecture, which is based on dilated convolution, can extract the deep change features effectively, and the character of “network in network” increases the depth and width of the network while keeping the computational budget constant. The change decision model is utilized to detect changes through the difference of extracted features. Finally, a change detection map is obtained via an uncertainty analysis, which combines the multi-resolution segmentation, with the output from the Siamese network. To validate the effectiveness of the proposed approach, we conducted experiments on multispectral images collected by the ZY-3 and GF-2 satellites. Experimental results demonstrate that our proposed method achieves comparable and better performance than mainstream methods in multi-sensor images change detection. |
topic |
multi-sensor image change detection siamese neural network dilated convolution object-based image analysis |
url |
https://www.mdpi.com/2072-4292/12/2/205 |
work_keys_str_mv |
AT moyangwang adeepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT kuntan adeepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT xiupingjia adeepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT xuewang adeepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT yuchen adeepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT moyangwang deepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT kuntan deepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT xiupingjia deepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT xuewang deepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages AT yuchen deepsiamesenetworkwithhybridconvolutionalfeatureextractionmoduleforchangedetectionbasedonmultisensorremotesensingimages |
_version_ |
1725327008700825600 |