In this paper we present an approach for performing object classification and segmentation in satellite images for the Maritime domain. We employ neural network architectures for object classification and segmentation tasks in order to identify different classes of objects in satellite imagery for the maritime domain, such as vessels, land (e.g., port terminals), clouds, etc. We compare the accuracy of different neural network architectures and present the results of our experimental evaluation.
Automatic Maritime Object Detection Using Satellite imagery
2020-10-05
271758 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Automatic Registration of Satellite Imagery
British Library Conference Proceedings | 1998
|Automatic Geolocation Correction of Satellite Imagery
British Library Online Contents | 2016
|Describing Object Shapes in Satellite Imagery
Online Contents | 2000
|Automatic DEM Generation and 3D Change Detection from Satellite Imagery
British Library Conference Proceedings | 2013
|