Difference-Focusing Fusion Decision Method: An Ensemble Learning Framework and Its Application in Improving Deep Learning Sea–Land Segmentation for Waterline Extraction in Synthetic Aperture Radar Imagery

Waterline extraction from synthetic aperture radar (SAR) images can be transformed into a sea-land segmentation task. However, two aspects of deep learning sea-land segmentation have been ignored in the literature: 1) deep learning models are commonly built using whole images rather than focusing on their sea-land transition parts and 2) a higher resolution input may not render a better segmentation result under the constraint of a fixed-size receptive field. Our investigation on the aspects indicates that focusing the modeling process on the sea-land transition parts can benefit the waterline extraction, and the highest resolution may not be the best choice for all pixels. We proposed masked soft intersection over union (MSIoU) loss and the difference-focusing fusion decision (DFFD) ensemble learning method. MSIoU loss incorporates the mask of the transition parts to focus the modeling process on the transition parts. The DFFD ensemble learning method imitates manual labeling and can avoid selecting the resolution of input images. The DFFD ensemble model’s member models segment an image’s sea and land areas at different resolutions. Then, its fusion model further recognizes the pixels where the member models inconsistently predict sea-land types. We applied the DFFD ensemble model to 10-m-resolution SAR images of the test set. Compared to the traditional single-resolution model, the DFFD ensemble model with MSIoU loss achieved a 10.32–12.58-m accuracy in waterline extraction with a 2.08–2.78-m error reduction in the study area. Moreover, the DFFD framework is independent of data and model choice and can be readily modified for other segmentation tasks.