Enhancing maritime search and rescue: Incremental unsupervised domain adaptation with synthetic data and pseudo-labeling
Juan P. Martinez-Esteso, Francisco J. Castellanos, Antonio Javier Gallego · Expert Systems with Applications · 2025
Maritime search and rescue operations are critical for saving lives in emergencies, where time is a decisive factor since delays can drastically reduce the chances of survival for those in distress. These missions are particularly challenging due to the inherent complexity of the maritime environment, marked by changing weather, dynamic sea states, and limited visibility. Developing reliable machine learning systems for this task typically requires large amounts of labeled data that capture all possible operating conditions. However, collecting and annotating such data is costly and often unfeasible in real-world maritime scenarios. To address this limitation, we propose a domain adaptation strategy for a segmentation-based detection model that estimates a probability map indicating the presence of human bodies at sea. The method enables unsupervised learning to adapt from a labeled synthetic domain to a real, unlabeled domain by employing a Domain-Adversarial Neural Network that aligns feature representations across domains, and an iterative pseudo-labeling process that selects high-confidence predictions on the target data to progressively refine the model. By leveraging synthetic data—automatically generated and labeled—our approach adapts effectively to real-world conditions without requiring manual annotation. Experimental results show that our method outperforms several state-of-the-art detectors while maintaining a lightweight architecture. Moreover, it generalizes well under diverse and adverse environmental conditions, including fog, rain, and low-light scenes, demonstrating its robustness and suitability for real-world deployment in critical rescue operations.