Weakly-Supervised Semantic Segmentation of Ships Using Thermal Imagery

TL;DR

This paper demonstrates that weakly-supervised learning with sparse labels can effectively segment ships in infrared imagery, significantly reducing labeling effort while maintaining high performance.

Contribution

It introduces a weakly-supervised approach for maritime ship segmentation in infrared images using minimal labeling, reducing annotation costs substantially.

Findings

Sparse labeling of 32 points per image achieves a Jaccard score of 0.756.

Weakly-supervised models perform comparably to fully supervised models in ship segmentation.

The approach enables scalable maritime surveillance with less manual annotation effort.

Abstract

The United States coastline spans 95,471 miles; a distance that cannot be effectively patrolled or secured by manual human effort alone. Unmanned Aerial Vehicles (UAVs) equipped with infrared cameras and deep-learning based algorithms represent a more efficient alternative for identifying and segmenting objects of interest - namely, ships. However, standard approaches to training these algorithms require large-scale datasets of densely labeled infrared maritime images. Such datasets are not publicly available and manually annotating every pixel in a large-scale dataset would have an extreme labor cost. In this work we demonstrate that, in the context of segmenting ships in infrared imagery, weakly-supervising an algorithm with sparsely labeled data can drastically reduce data labeling costs with minimal impact on system performance. We apply weakly-supervised learning to an unlabeled dataset of 7055 infrared images sourced from the Naval Air Warfare Center Aircraft Division (NAWCAD). We find that by sparsely labeling only 32 points per image, weakly-supervised segmentation models can still effectively detect and segment ships, with a Jaccard score of up to 0.756.