← Marketplace
Truck detection
Description
An algorithm that detects and quantifies trucks in Pléiades imagery using wide area object detection. Truck detection can be used for supply chain and logistics management, traffic management, and urban planning.
Technical information
| Source | Pléiades tasking or catalog collections |
| Compatibility | - The STAC item should be a Pléiades 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 |
| Output data format | GeoJSON file: with point detections corresponding to the location of trucks |
| 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
The algorithm has been qualified on a large set of data encompassing different types of landscapes worldwide by a third party, with a good level of performances. The algorithm performance will vary according to geography and imagery features.
This algorithm was tested by a 3rd party using a validation set, consisting of approximately 5,000 marked trucks in 50 countries spanning 6 continents. The training set contains 50,000 images and spans many variable conditions including time of day, time of year, terrain, configuration of vehicles, etc.
Further information
For more information, please visit the technical documentation.