A satellite image offshore ship identification method based on Faster R-CNN
The invention provides a satellite image offshore ship identification method based on Faster R-CNN, which is characterized by comprising the following steps of: segmenting original satellite image data by using a satellite image segmentation algorithm based on target selection, adding a training sam...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention provides a satellite image offshore ship identification method based on Faster R-CNN, which is characterized by comprising the following steps of: segmenting original satellite image data by using a satellite image segmentation algorithm based on target selection, adding a training sample based on a generative adversarial network, and using the Faster R-CNN algorithm to establish a satellite image offshore ship training data set, and using the Faster R- CNN algorithm and a training data set to generate a satellite image offshore ship recognition model, establishing a latitude andlongitude matching mode, supporting accurate latitude and longitude matching based on the pixel and latitude and longitude mapping relation, and achieving recognition of an offshore ship in a satellite image. According to the invention, a practical offshore ship identification technical scheme is provided based on the satellite image, the processing speed is high, the precision is high, and one or more ship targets of di |
---|