Sports Facilities Detection
Detects baseball fields, tennis courts, soccer fields, and stadiums in cities and towns.
Sports Facilities Detection is a Processing Block for identifying sports facilities such as baseball parks, tennis courts, soccer fields, and stadiums in satellite images in .png or .jpeg or .jpg or .tiff format. Block can detect sports facilities in images with ground sampling distance (GSD) of 0.55m or less. Output is provided as images with detection bounding boxes overlayed on the sports facilites and detection details in a .json file.The block is trained on data-set obtained from South-Eastern Asia.
- Pléiades Display (Streaming) -> Sports Facilities Detection
- Pléiades Display (Download) -> DIMAP -> GeoTIFF Conversion -> Sports Facilities Detection
Note: This block needs to be used without Raster Tiling. Pléiades Reflectance (Download) is currently not supported.
The algorithm uses generative deep learning techniques and CNN-based Artificial Neural Network architecture to achieve the computer vision objective. The solution is built in Python and uses Tensorflow at backend as deep learning framework. The algorithm processes satellite images in GeoTIFF, TIFF, PNG, JPG or JPEG formats, with no limitations on image dimensions.
The use cases for this block are infrastructure monitoring, urban planning and construction.
|Supported input data||Input is required as a set of PNG, JPEG or TIFF images. The image is expected to have Ground Sampling Distance (GSD) less than 0.55 m|
|Output data format||The output is resultant image with detection bounding boxes overlayed onto the input images|
|Algorithm Training Data Details||The algorithm has been trained using custom built data sets from satellite images captured over South Eastern Asian region.|
|Performance||0.5 IoU and has detection of 0.5mAP on satellite images with GSD 0.55m|
Fore more information, visit the provider website here.
Terms & Conditions
View the End User License Agreement conditions.