← Marketplace
Upsampling
Description
An algorithm that improves the spatial resolution of Pléiades Neo imagery from 30 cm to 10 cm. Upsampling can be used as a pre-processing step before change detection, vegetation detection, infrastructure detection, fire risk estimation, and land use management.
Technical information
Source | Pléiades Neo tasking or catalog collections |
Compatibility | - The STAC item should be a Pléiades Neo image of the display radiometric processing level - The STAC item should have been added to storage in 2023 or later |
Required parameters | - Console: If your chosen input data meets the above specifications you will be able to run your job - API: You will need to input an Output title and the Input data |
Bands to unsample | You need to specify if you want to upsample the red, green, and blue bands or the NIR, red edge, and deep blue bands |
Output data format | GeoTIFF file with an upsampled spatial resolution |
Output | The result will be added to your account as a STAC item in a new STAC collection. You can retrieve the resulting data in one of the following ways: - Open the console, go to Data management → Jobs - Retrieve the results via the API |
Algorithm performance and training data
Tensorflow is used to build a convolutional neural network (CNN) for super-resolution. Unlike other conventional super-resolution networks, high-resolution and low-resolution images are from different satellites. In the case of Pléiades Neo super-resolution, 10 cm GSD images are used for high resolution.
It helps users to have a clearer view of their areas of interest at a much lower cost compared to commercial imagery.
Remark: The algorithm also works with Pléiades Neo (Analytic), but it is not trained on 16-bit images. There might be color differences after applying super-resolution to the Pléiades Neo (Analytic) 16-bit product.
Processing time: Without considering preprocessing, it takes ~16 minutes to enhance a 3.92 sqkm (6600 x 6600 pixels) Pléiades Neo image using GPU (Nvidia Tesla K80) provided by UP42.
Limitation: Super-resolution cannot express features that are not shown in the original image.
Further information
For more information, please visit the technical documentation.