...
The current version of the model has been trained on Sentinel-1 scenes from several geographic areas that we were annotated by hand by subject matter experts. These areas include water bodies around Bahamas, Ghana, Madagascar, Persian Gulf, Argentina, Taiwan, and Singapore. The model predicts the positions of vessels, and assigns each prediction a confidence score. The only Detections with a confidence score > .9 are displayed in Skylight. The other attribute that the model predicts is vessel length. Specifically, the Docker container will take in decompressed Sentinel-1 scenes, and save the crops of vessels detected in those scenes. The
To distinguish moving ships from static objects like islands, platforms. and other static non-vessel structures, the model is trained on data that includes overlapping images captured at different times. It will compare the images to distinguish moving ships from static objects like islands, platforms. and other static non-vessel structuresThe model compares these images and learns to disregard static images.