MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network
In order to acquire a high resolution multispectral (HRMS) image with the same spectral resolution as multispectral (MS) image and the same spatial resolution as panchromatic (PAN) image, pansharpening, a typical and hot image fusion topic, has been well researched. Various pansharpening methods tha...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/6/1200 |
| _version_ | 1827697050967343104 |
|---|---|
| author | Wenqing Wang Zhiqiang Zhou Han Liu Guo Xie |
| author_facet | Wenqing Wang Zhiqiang Zhou Han Liu Guo Xie |
| author_sort | Wenqing Wang |
| collection | DOAJ |
| description | In order to acquire a high resolution multispectral (HRMS) image with the same spectral resolution as multispectral (MS) image and the same spatial resolution as panchromatic (PAN) image, pansharpening, a typical and hot image fusion topic, has been well researched. Various pansharpening methods that are based on convolutional neural networks (CNN) with different architectures have been introduced by prior works. However, different scale information of the source images is not considered by these methods, which may lead to the loss of high-frequency details in the fused image. This paper proposes a pansharpening method of MS images via multi-scale deep residual network (MSDRN). The proposed method constructs a multi-level network to make better use of the scale information of the source images. Moreover, residual learning is introduced into the network to further improve the ability of feature extraction and simplify the learning process. A series of experiments are conducted on the QuickBird and GeoEye-1 datasets. Experimental results demonstrate that the MSDRN achieves a superior or competitive fusion performance to the state-of-the-art methods in both visual evaluation and quantitative evaluation. |
| first_indexed | 2024-03-10T13:01:59Z |
| format | Article |
| id | doaj.art-44393a7b64864d1084b38f5503da7492 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T13:01:59Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-44393a7b64864d1084b38f5503da74922023-11-21T11:26:11ZengMDPI AGRemote Sensing2072-42922021-03-01136120010.3390/rs13061200MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual NetworkWenqing Wang0Zhiqiang Zhou1Han Liu2Guo Xie3School of Automation and Information Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Automation and Information Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Automation and Information Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Automation and Information Engineering, Xi’an University of Technology, Xi’an 710048, ChinaIn order to acquire a high resolution multispectral (HRMS) image with the same spectral resolution as multispectral (MS) image and the same spatial resolution as panchromatic (PAN) image, pansharpening, a typical and hot image fusion topic, has been well researched. Various pansharpening methods that are based on convolutional neural networks (CNN) with different architectures have been introduced by prior works. However, different scale information of the source images is not considered by these methods, which may lead to the loss of high-frequency details in the fused image. This paper proposes a pansharpening method of MS images via multi-scale deep residual network (MSDRN). The proposed method constructs a multi-level network to make better use of the scale information of the source images. Moreover, residual learning is introduced into the network to further improve the ability of feature extraction and simplify the learning process. A series of experiments are conducted on the QuickBird and GeoEye-1 datasets. Experimental results demonstrate that the MSDRN achieves a superior or competitive fusion performance to the state-of-the-art methods in both visual evaluation and quantitative evaluation.https://www.mdpi.com/2072-4292/13/6/1200pansharpeningmultispectral imagepanchromatic imagedeep residual networkmulti-scale network |
| spellingShingle | Wenqing Wang Zhiqiang Zhou Han Liu Guo Xie MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network Remote Sensing pansharpening multispectral image panchromatic image deep residual network multi-scale network |
| title | MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network |
| title_full | MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network |
| title_fullStr | MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network |
| title_full_unstemmed | MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network |
| title_short | MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network |
| title_sort | msdrn pansharpening of multispectral images via multi scale deep residual network |
| topic | pansharpening multispectral image panchromatic image deep residual network multi-scale network |
| url | https://www.mdpi.com/2072-4292/13/6/1200 |
| work_keys_str_mv | AT wenqingwang msdrnpansharpeningofmultispectralimagesviamultiscaledeepresidualnetwork AT zhiqiangzhou msdrnpansharpeningofmultispectralimagesviamultiscaledeepresidualnetwork AT hanliu msdrnpansharpeningofmultispectralimagesviamultiscaledeepresidualnetwork AT guoxie msdrnpansharpeningofmultispectralimagesviamultiscaledeepresidualnetwork |