Cross-modal change detection flood extraction based on convolutional neural network
Flood events are often accompanied by rainy weather, which limits the applicability of optical satellite images, whereas synthetic aperture radar (SAR) is less sensitive to weather and sunlight conditions. Although remarkable progress has been made in flood detection using heterogeneous multispectra...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-03-01
|
Series: | International Journal of Applied Earth Observations and Geoinformation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223000195 |
_version_ | 1811163485222993920 |
---|---|
author | Xiaoning He Shuangcheng Zhang Bowei Xue Tong Zhao Tong Wu |
author_facet | Xiaoning He Shuangcheng Zhang Bowei Xue Tong Zhao Tong Wu |
author_sort | Xiaoning He |
collection | DOAJ |
description | Flood events are often accompanied by rainy weather, which limits the applicability of optical satellite images, whereas synthetic aperture radar (SAR) is less sensitive to weather and sunlight conditions. Although remarkable progress has been made in flood detection using heterogeneous multispectral and SAR images, there is a lack of publicly available large-scale datasets and more efforts are required for exploiting deep neural networks in heterogeneous flood detection. This study constructed a pre-disaster Sentinel-2 and post-disaster Sentinel-1 heterogeneous flood mapping dataset named CAU-Flood containing 18 study plots with careful image preprocessing and human annotation. A new deep convolutional neural network (CNN), named cross-modal change detection network (CMCDNet), was also proposed for flood detection using multispectral and SAR images. The proposed network employs a encoder-decoder structure and performs feature fusion at multiple stages using gating and self-attention modules. Furthermore, the network overcomes the feature misalignment issue during decoding by embedding a feature alignment module in the upsampling operation. The proposed CMCDNet outperformed SOTA methods in terms of flood detection accuracy and achieved an intersection over union (IoU) of 89.84%. The codes and datasets are available at: https://github.com/CAU-HE/CMCDNet. |
first_indexed | 2024-04-10T15:06:39Z |
format | Article |
id | doaj.art-a7f68d550adb4e1097f0b23c74823264 |
institution | Directory Open Access Journal |
issn | 1569-8432 |
language | English |
last_indexed | 2024-04-10T15:06:39Z |
publishDate | 2023-03-01 |
publisher | Elsevier |
record_format | Article |
series | International Journal of Applied Earth Observations and Geoinformation |
spelling | doaj.art-a7f68d550adb4e1097f0b23c748232642023-02-15T04:27:29ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-03-01117103197Cross-modal change detection flood extraction based on convolutional neural networkXiaoning He0Shuangcheng Zhang1Bowei Xue2Tong Zhao3Tong Wu4College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China; Geovis Spatial Technology Co., Ltd, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China; Key Laboratory of Western China’s Mineral Resource and Geological Engineering, Ministry of Education, Xi’an 710054, China; State Key Laboratory of Geo-Information Engineering, Xi’an 710054, China; Corresponding author at: College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China.Geovis Spatial Technology Co., Ltd, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaFlood events are often accompanied by rainy weather, which limits the applicability of optical satellite images, whereas synthetic aperture radar (SAR) is less sensitive to weather and sunlight conditions. Although remarkable progress has been made in flood detection using heterogeneous multispectral and SAR images, there is a lack of publicly available large-scale datasets and more efforts are required for exploiting deep neural networks in heterogeneous flood detection. This study constructed a pre-disaster Sentinel-2 and post-disaster Sentinel-1 heterogeneous flood mapping dataset named CAU-Flood containing 18 study plots with careful image preprocessing and human annotation. A new deep convolutional neural network (CNN), named cross-modal change detection network (CMCDNet), was also proposed for flood detection using multispectral and SAR images. The proposed network employs a encoder-decoder structure and performs feature fusion at multiple stages using gating and self-attention modules. Furthermore, the network overcomes the feature misalignment issue during decoding by embedding a feature alignment module in the upsampling operation. The proposed CMCDNet outperformed SOTA methods in terms of flood detection accuracy and achieved an intersection over union (IoU) of 89.84%. The codes and datasets are available at: https://github.com/CAU-HE/CMCDNet.http://www.sciencedirect.com/science/article/pii/S1569843223000195Heterogeneous data fusionOptical-radarFlood extractionCross-modality |
spellingShingle | Xiaoning He Shuangcheng Zhang Bowei Xue Tong Zhao Tong Wu Cross-modal change detection flood extraction based on convolutional neural network International Journal of Applied Earth Observations and Geoinformation Heterogeneous data fusion Optical-radar Flood extraction Cross-modality |
title | Cross-modal change detection flood extraction based on convolutional neural network |
title_full | Cross-modal change detection flood extraction based on convolutional neural network |
title_fullStr | Cross-modal change detection flood extraction based on convolutional neural network |
title_full_unstemmed | Cross-modal change detection flood extraction based on convolutional neural network |
title_short | Cross-modal change detection flood extraction based on convolutional neural network |
title_sort | cross modal change detection flood extraction based on convolutional neural network |
topic | Heterogeneous data fusion Optical-radar Flood extraction Cross-modality |
url | http://www.sciencedirect.com/science/article/pii/S1569843223000195 |
work_keys_str_mv | AT xiaoninghe crossmodalchangedetectionfloodextractionbasedonconvolutionalneuralnetwork AT shuangchengzhang crossmodalchangedetectionfloodextractionbasedonconvolutionalneuralnetwork AT boweixue crossmodalchangedetectionfloodextractionbasedonconvolutionalneuralnetwork AT tongzhao crossmodalchangedetectionfloodextractionbasedonconvolutionalneuralnetwork AT tongwu crossmodalchangedetectionfloodextractionbasedonconvolutionalneuralnetwork |