The algorithm identifies all pixels that are part of a tree and its shadow and calculates the heights of detected trees in SPOT, Pléiades, or Pléiades Neo display imagery. The results are the following:
- A GeoTIFF file that maps the probability of each pixel being part of a shadow
- A GeoTIFF file that maps the probability of each pixel being part of a tree
- A GeoJSON file with polygons representing the heights of detected trees
Tree and tree height detection can be used for infrastructure vegetation risk monitoring, urban planning, and construction.
An input SPOT image of Paihuano (Chile)
A shadow probability map
A tree probability map
Detected tree height polygons drawn on the input image
See more on the marketplace.
The algorithm has been developed using tens of thousands of semantically annotated images.
The accuracy is as follows:
- On isolated objects, with the entire shadow on level ground: 1–2 m
- In worse conditions: up to 8 m
The STAC item must be a display data product from one of the following collections: SPOT, Pléiades, or Pléiades Neo.
The STAC item must be CNAM-compatible. Check that the STAC item has been added to storage in 2023 or later.
Required parameters
Input imagery
You need to specify the STAC items you want to apply the process to.
Output title
You need to specify the title of the output objects. This title will be assigned to the resulting STAC item and STAC collection.
Use the detection-trees-heights-spacept name ID for the processing API.
A sample input payload for the process
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"
}
}
| Parameter | Overview |
|---|---|
inputs.title | object / required The title of the output objects: STAC item and STAC collection. |
inputs.item | object / required The STAC item link in the following format: https://api.up42.com/v2/assets/stac/collections/{collection-id}/items/{item-id} |