Search
Abstract
The aim of the project was to analyze the possibility of using machine learning and computer vision to identify (indicate the location) of all sea-going vessels located in the selected area of the open sea and to classify the main attributes of the vessel. The key elements of the project were to download data from the Sentinel-1 satellite [1], download data on the sea vessels [2], then automatically tag data and develop a detection and classification algorithm. The results obtained from the YOLOv7 model on the test set were Mean Average Precision (mAP@.5) = 91% and F1-score = 93% for the single-class ship detection task. When combining the task of ship detection with a ship’s length and width classification, Mean Average Precision for all classes was 40%, f1-score was 41%
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language:
- English
- Publication year:
- 2023
- Bibliographic description:
- Kobiela D., Berezowski T.: Classification of Sea Going Vessels Properties Using SAR Satellite Images// / : , 2023,
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/igarss52108.2023.10283395
- Sources of funding:
-
- Project -
- Verified by:
- Gdańsk University of Technology
seen 71 times
Recommended for you
Orientation-aware ship detection via a rotation feature decoupling supported deep learning approach
- X. Chen,
- H. Wu,
- B. Han
- + 3 authors
Cascade Object Detection and Remote Sensing Object Detection Method Based on Trainable Activation Function
- S. N. Shivappriya,
- M. J. P. Priyadarsini,
- A. Stateczny
- + 2 authors