Ship Detection in Satellite Optical Imagery
Benjamin Carl Smith, Sean Chester, Yvonne Coady · 2020
Deep learning ship detection in satellite optical imagery suffers from false positive occurrences with clouds, landmasses, and man-made objects that interfere with correct classification of ships, typically limiting class accuracy scores to 88%. This work explores the tensions between customization strategies, class accuracy rates, training times, and costs in cloud-based solutions. We demonstrate how a custom U-Net can achieve 92% class accuracy over a validation dataset and 68% over a target dataset. Trade-offs with extensions to this effort, such as a refining method of offline hard example mining, are also considered.