Co-registration

Detection and matching of features from satellite images.


Analytics platform discontinued after January 31, 2024

The current analytics platform will be discontinued after January 31, 2024, and will be replaced by new advanced processing functionalities. This change will affect projects, workflows, jobs, data blocks, processing blocks, and custom blocks. For more information, see the blog post.

Description

A processing block that performs the spatial alignment of 2 images based on the calculation of translation, rotation, and scale variation.

See this block on the marketplace.

How it works

This block has no configurable JSON parameters.

It ensures that the images become spatially aligned and any feature in the images overlaps. This block is based on the DFT image registration Python package.

This block currently accepts only two images, where the second image is geometrically aligned with the first image.

The algorithm has the following limitations:

  • The input images must have the same size and shape.
  • The input images must be in GeoTIFF format.

It's recommended to select an AOI greater than 1 square kilometer and to use the geometric filter contains.

Compatibility

Catalog collections

Use in combination with Processing from Storage.

Example

A workflow with the following blocks:

{
  "up42-processing-from-storage:1": {
    "asset_ids": ["00210895-5405-4c0r-9bca-ccca551776f9", "23116554-0344-5f1c-6aba-deeb751770d7"]
  },
  "data-conversion-dimap:1": {
    "ms": true,
    "pan": false,
    "bbox": null,
    "contains": null,
    "intersects": null,
    "clip_to_aoi": false
  },
  "up42-coregistration:1": {}
}

Capabilities

Input

raster
up42_standard
bands
[
  "red",
  "green",
  "blue"
]
formatGTiff
sensor
{
  "or": [
    "Pleiades",
    "SPOT"
  ]
}

Output

To know more please check the block capabilities specifications.