Remote Sensing· 2016Q1
Pansharpening by Convolutional Neural Networks
- 1,111citations
- Q1SCImago
- 2016year
Short summary
A new pansharpening method using a three-layer convolutional neural network (CNN) architecture, augmented with nonlinear radiometric indices, achieves state-of-the-art results on three datasets.
AI-generated from the title and abstract; the full text is not read.
Key points
- A three-layer CNN architecture, originally for super-resolution, is adapted for pansharpening.
- Input data is augmented with nonlinear radiometric indices to improve performance.
- The proposed method achieves competitive results against state-of-the-art techniques.
- Performance is validated using both full-reference and no-reference metrics, as well as visual inspection.
AI-generated from the title and abstract; the full text is not read.
Abstract
A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices typical of remote sensing. Experiments on three representative datasets show the proposed method to provide very promising results, largely competitive with the current state of the art in terms of both full-reference and no-reference metrics, and also at a visual inspection.
The authors' abstract, as published at the source. Remote Sensing, 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Media Technology
Media TechnologyEngineering