Published October 9, 2020
| Version v1
Conference paper
Open
Automatic Maritime Object Detection Using Satellite imagery
- 1. MarineTraffic
- 2. NATO-STO-CMRE
- 3. University of the Aegean, MarineTraffic
Description
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.
Files
IEEE_Oceans.pdf
Files
(611.0 kB)
Name | Size | Download all |
---|---|---|
md5:b65329c846627b4a16db78d633ca9464
|
611.0 kB | Preview Download |