File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.jag.2022.102745
- Scopus: eid_2-s2.0-85126629629
- WOS: WOS:000783884200001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Progressive spatiotemporal image fusion with deep neural networks
Title | Progressive spatiotemporal image fusion with deep neural networks |
---|---|
Authors | |
Keywords | Convolutional neural network Deep learning Landsat MODIS Spatiotemporal fusion |
Issue Date | 2022 |
Citation | International Journal of Applied Earth Observation and Geoinformation, 2022, v. 108, article no. 102745 How to Cite? |
Abstract | Spatiotemporal image fusion (STIF) provides a feasible and effective solution for generating satellite images with high spatial and temporal resolution. As deep learning-based fusion algorithms show great potential in generating high-quality images, we propose a novel deep learning model, namely a deep progressive spatiotemporal fusion network (DPSTFN), which is coupled with pansharpening and super-resolution learning processes to satisfy requirements of STIF based on Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat data. First, a pansharpening process is adopted to make full use of two MODIS bands with 250 m spatial resolution. Second, a super-resolution process enhances the spatial information that existed in coarse-resolution images to alleviate the enormous spatial resolution gap between MODIS and Landsat images. Third, combining the aforementioned two auxiliary processes, a progressive spatiotemporal fusion framework is proposed to generate deliberate and robust fusion results. Experiments are conducted using two MODIS-Landsat datasets of distinctive landforms to evaluate the performance of DPSTFN. The results of the subjective and objective evaluation show that our proposed network performs better than the state-of-the-art traditional STIF algorithms Fit-FC and RASTFM, and the deep learning-based algorithms EDCSTFN and StfNet. |
Persistent Identifier | http://hdl.handle.net/10722/329794 |
ISSN | 2023 Impact Factor: 7.6 2023 SCImago Journal Rankings: 2.108 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cai, Jiajun | - |
dc.contributor.author | Huang, Bo | - |
dc.contributor.author | Fung, Tung | - |
dc.date.accessioned | 2023-08-09T03:35:23Z | - |
dc.date.available | 2023-08-09T03:35:23Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | International Journal of Applied Earth Observation and Geoinformation, 2022, v. 108, article no. 102745 | - |
dc.identifier.issn | 1569-8432 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329794 | - |
dc.description.abstract | Spatiotemporal image fusion (STIF) provides a feasible and effective solution for generating satellite images with high spatial and temporal resolution. As deep learning-based fusion algorithms show great potential in generating high-quality images, we propose a novel deep learning model, namely a deep progressive spatiotemporal fusion network (DPSTFN), which is coupled with pansharpening and super-resolution learning processes to satisfy requirements of STIF based on Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat data. First, a pansharpening process is adopted to make full use of two MODIS bands with 250 m spatial resolution. Second, a super-resolution process enhances the spatial information that existed in coarse-resolution images to alleviate the enormous spatial resolution gap between MODIS and Landsat images. Third, combining the aforementioned two auxiliary processes, a progressive spatiotemporal fusion framework is proposed to generate deliberate and robust fusion results. Experiments are conducted using two MODIS-Landsat datasets of distinctive landforms to evaluate the performance of DPSTFN. The results of the subjective and objective evaluation show that our proposed network performs better than the state-of-the-art traditional STIF algorithms Fit-FC and RASTFM, and the deep learning-based algorithms EDCSTFN and StfNet. | - |
dc.language | eng | - |
dc.relation.ispartof | International Journal of Applied Earth Observation and Geoinformation | - |
dc.subject | Convolutional neural network | - |
dc.subject | Deep learning | - |
dc.subject | Landsat | - |
dc.subject | MODIS | - |
dc.subject | Spatiotemporal fusion | - |
dc.title | Progressive spatiotemporal image fusion with deep neural networks | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.jag.2022.102745 | - |
dc.identifier.scopus | eid_2-s2.0-85126629629 | - |
dc.identifier.volume | 108 | - |
dc.identifier.spage | article no. 102745 | - |
dc.identifier.epage | article no. 102745 | - |
dc.identifier.eissn | 1872-826X | - |
dc.identifier.isi | WOS:000783884200001 | - |