Ship classification from overhead imagery using synthetic data and domain adaptation
This work addresses the unsolved problem of ship classification for maritime surveillance, but it is incremental as it builds on existing methods by introducing synthetic data to mitigate data scarcity.
The paper tackles the problem of ship classification from overhead imagery by addressing the lack of substantial ground truth data, using a large synthetic dataset of 200k images generated with the Unity gaming engine and 3D models, which dramatically increases classification performance, especially with few annotated training images.
In this paper, we revisit the problem of classifying ships (maritime vessels) detected from overhead imagery. Despite the last decade of research on this very important and pertinent problem, it remains largely unsolved. One of the major issues with the detection and classification of ships and other objects in the maritime domain is the lack of substantial ground truth data needed to train state-of-the-art machine learning algorithms. We address this issue by building a large (200k) synthetic image dataset using the Unity gaming engine and 3D ship models. We demonstrate that with the use of synthetic data, classification performance increases dramatically, particularly when there are very few annotated images used in training.