Insight Into the Collocation of Multi-Source Satellite Imagery for Multi-Scale Vessel Detection
This work addresses domain adaptation challenges in maritime surveillance for remote sensing applications, but it is incremental as it builds on existing deep learning methods for multi-source imagery.
The paper tackled the problem of applying deep learning models trained on one satellite imagery dataset to others with different spatial resolutions and radiometric features, achieving a 5-20% improvement in average precision for vessel detection when using multi-source data and limited training images.
Ship detection from satellite imagery using Deep Learning (DL) is an indispensable solution for maritime surveillance. However, applying DL models trained on one dataset to others having differences in spatial resolution and radiometric features requires many adjustments. To overcome this issue, this paper focused on the DL models trained on datasets that consist of different optical images and a combination of radar and optical data. When dealing with a limited number of training images, the performance of DL models via this approach was satisfactory. They could improve 5-20% of average precision, depending on the optical images tested. Likewise, DL models trained on the combined optical and radar dataset could be applied to both optical and radar images. Our experiments showed that the models trained on an optical dataset could be used for radar images, while those trained on a radar dataset offered very poor scores when applied to optical images.