Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method
Lakes have been identified as an important indicator of climate change and a finer lake area can better reflect the changes. In this paper, we propose an effective unsupervised deep gradient network (UDGN) to generate a higher resolution lake area from remote sensing images. By exploiting the power...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/12/1937 |
id |
doaj-63f93b45611d46de8657eee2002b5f36 |
---|---|
record_format |
Article |
spelling |
doaj-63f93b45611d46de8657eee2002b5f362020-11-25T04:02:22ZengMDPI AGRemote Sensing2072-42922020-06-01121937193710.3390/rs12121937Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution MethodMengjiao Qin0Linshu Hu1Zhenhong Du2Yi Gao3Lianjie Qin4Feng Zhang5Renyi Liu6School of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaKey Laboratory of Environmental Change and Natural Disaster of Ministry of Education, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaLakes have been identified as an important indicator of climate change and a finer lake area can better reflect the changes. In this paper, we propose an effective unsupervised deep gradient network (UDGN) to generate a higher resolution lake area from remote sensing images. By exploiting the power of deep learning, UDGN models the internal recurrence of information inside the single image and its corresponding gradient map to generate images with higher spatial resolution. The gradient map is derived from the input image to provide important geographical information. Since the training samples are only extracted from the input image, UDGN can adapt to different settings per image. Based on the superior adaptability of the UDGN model, two strategies are proposed for super-resolution (SR) mapping of lakes from multispectral remote sensing images. Finally, Landsat 8 and MODIS (moderate-resolution imaging spectroradiometer) images from two study areas on the Tibetan Plateau in China were used to evaluate the performance of UDGN. Compared with four unsupervised SR methods, UDGN obtained the best SR results as well as lake extraction results in terms of both quantitative and visual aspects. The experiments prove that our approach provides a promising way to break through the limitations of median-low resolution remote sensing images in lake change monitoring, and ultimately support finer lake applications.https://www.mdpi.com/2072-4292/12/12/1937unsupervised super-resolutionlakeremote sensingresidual networkgradient map |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mengjiao Qin Linshu Hu Zhenhong Du Yi Gao Lianjie Qin Feng Zhang Renyi Liu |
spellingShingle |
Mengjiao Qin Linshu Hu Zhenhong Du Yi Gao Lianjie Qin Feng Zhang Renyi Liu Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method Remote Sensing unsupervised super-resolution lake remote sensing residual network gradient map |
author_facet |
Mengjiao Qin Linshu Hu Zhenhong Du Yi Gao Lianjie Qin Feng Zhang Renyi Liu |
author_sort |
Mengjiao Qin |
title |
Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method |
title_short |
Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method |
title_full |
Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method |
title_fullStr |
Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method |
title_full_unstemmed |
Achieving Higher Resolution Lake Area from Remote Sensing Images Through an Unsupervised Deep Learning Super-Resolution Method |
title_sort |
achieving higher resolution lake area from remote sensing images through an unsupervised deep learning super-resolution method |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-06-01 |
description |
Lakes have been identified as an important indicator of climate change and a finer lake area can better reflect the changes. In this paper, we propose an effective unsupervised deep gradient network (UDGN) to generate a higher resolution lake area from remote sensing images. By exploiting the power of deep learning, UDGN models the internal recurrence of information inside the single image and its corresponding gradient map to generate images with higher spatial resolution. The gradient map is derived from the input image to provide important geographical information. Since the training samples are only extracted from the input image, UDGN can adapt to different settings per image. Based on the superior adaptability of the UDGN model, two strategies are proposed for super-resolution (SR) mapping of lakes from multispectral remote sensing images. Finally, Landsat 8 and MODIS (moderate-resolution imaging spectroradiometer) images from two study areas on the Tibetan Plateau in China were used to evaluate the performance of UDGN. Compared with four unsupervised SR methods, UDGN obtained the best SR results as well as lake extraction results in terms of both quantitative and visual aspects. The experiments prove that our approach provides a promising way to break through the limitations of median-low resolution remote sensing images in lake change monitoring, and ultimately support finer lake applications. |
topic |
unsupervised super-resolution lake remote sensing residual network gradient map |
url |
https://www.mdpi.com/2072-4292/12/12/1937 |
work_keys_str_mv |
AT mengjiaoqin achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod AT linshuhu achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod AT zhenhongdu achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod AT yigao achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod AT lianjieqin achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod AT fengzhang achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod AT renyiliu achievinghigherresolutionlakeareafromremotesensingimagesthroughanunsuperviseddeeplearningsuperresolutionmethod |
_version_ |
1724443309248610304 |