Ship detection

An algorithm that detects ships in SPOT imagery.


Overview

The algorithm uses object detection in SPOT display imagery to detect ships. The result is a GeoJSON file with polygons drawn around detected ships.

Ship detection can be used for maritime surveillance, port and harbor management, and fishing activity detection.

An input SPOT image of the Port of Rotterdam (Netherlands)

Detected ship polygons drawn on the input image


See more on the marketplace.

Performance

For optimal results, the algorithm must be used to detect ships larger than 26 m. You can use it to detect smaller ships, but the results might not be as accurate.

Scenarios represented in the training data:

  • Different cloud coverage
  • Different maritime conditions

Requirements for input imagery

The data item must be a supported data product:

  • SPOT catalog: Display

The data item must be CNAM-compatible. Check that the data item has been added to storage in 2023 or later.

Input parameters

You must specify the data items you want to apply the process to.

You must specify the title of the output data item.

API input

Use the detection-ships-airbus name ID for the processing API.

JSON
{
"inputs": {
"title": "Processing imagery over Berlin",
"item": "https://api.up42.com/v2/assets/stac/collections/21c0b14e-3434-4675-98d1-f225507ded99/items/23e4567-e89b-12d3-a456-426614174000"
}
}
ParameterOverview
inputs.title

object | required

The title of the output data item.

inputs.item

object | required

A link to the data item in the following format: https://api.up42.com/v2/assets/stac/collections/{collection-id}/items/{item-id}.


Last updated: