Maritime search and rescue (SAR) missions require rapid and resource-efficient exploration of wide search areas under severe uncertainty in target location, while actual operational time is highly constrained. To support effective decision-making in such conditions, search planning is commonly formulated as a grid-based coverage path planning problem. However, traditional heuristic- based search patterns used in practice, such as parallel track search and expanding square search, offer limited adaptability because they do not explicitly reflect probability distributions that evolve due to environmental factors such as wind and ocean currents. To address these limitations, this study proposes a maskable Proximal Policy Optimization (PPO) framework for efficient grid-based search, motivated by the operational characteristics of maritime SAR missions. The proposed approach integrates domain- specific action masking rules into the policy optimization process to restrict invalid or inefficient actions during learning and execution. By guiding the agent toward feasible movements and high-priority regions of the search space, the framework promotes structured exploration behavior and stable policy learning in large-scale grid environments with sparse and unevenly distributed targets. The learning environment is constructed to reflect realistic maritime search conditions by incorporating probability distributions derived from drift particle simulations, and the search problem is modeled as a Markov decision process. The proposed method is evaluated under multiple target distribution scenarios and compared with representative heuristic search strategies, including parallel track search, nearest neighbor, expanding square search, and 2-optimization. Search performance is primarily assessed in terms of total search cost, measured by the cumulative movement steps required to complete the search task. Experimental results demonstrate that the maskable PPO consistently achieves the lowest total search cost across all tested environments. In particular, it requires substantially fewer movement steps than parallel track search and nearest neighbor methods, while maintaining comparable or superior efficiency relative to expanding square search and 2-optimization, depending on the target distribution. These results indicate that the proposed approach effectively learns coverage paths that reflect the underlying probability distribution of the environment. Overall, this study demonstrates that action- masking-based reinforcement learning provides a practical and scalable alternative to conventional heuristic search strategies for maritime SAR missions and establishes a foundation for adaptive search planning under realistic environmental uncertainty.

Accurate building representation in national digital maps is essential for ensuring reliable geospatial analyses and supporting policy and administrative decision-making. However, the current quality inspection system in Korea relies on manual sampling-based verification, which inspects only about 30% of each map sheet and therefore risks overlooking errors in the remaining data. In particular, depiction errors in building polygons—such as inaccurate outlines or positional shifts—can significantly degrade the reliability of digital maps, especially when they are used as ground truth for training and validating Artificial Intelligence (AI) models. This study proposes an automated verification framework that combines the complementary strengths of two segmentation approaches: SegFormer, which provides robust contextual awareness for detecting building areas, and Segment Anything Model 2 (SAM 2), which offers precise boundary delineation through prompt-based segmentation. To this end, we designed a context- and boundary-aware segmentation pipeline: SegFormer first identifies candidate building regions from high-resolution true orthoimages, while SAM 2 refines the building outlines at the object level using bounding-box prompts and a probability map derived from both models. This integration resolves under- segmentation issues observed in standalone SegFormer outputs and enables precise extraction of individual building footprints. Experiments were conducted in Seoul using a 2022 true orthoimage (Ground Sample Distance [GSD], 0.12 m) and the 1:5,000 national digital map. The results demonstrated a substantial improvement in segmentation accuracy: the one-to-one matching ratio between building objects increased from 61.46% (SegFormer alone) to 97.56% with the proposed method, while boundary accuracy (Boundary Intersection over Union, BIoU) improved from 65.85% to 72.60%. In depiction error verification, the method achieved 100% recall in detecting erroneous building polygons, ensuring that no actual errors were omitted. Although the precision was relatively low (6.93%) due to false alarms caused by occlusions and resolution limitations, this conservative detection approach offers a practical advantage: only error candidates need to be manually reviewed, reducing the inspection workload by approximately 75% compared to full manual verification. The proposed method highlights the potential of AI-based automation for nationwide digital map quality management. By fusing contextual and boundary-aware segmentation, it not only improves the precision of building footprint extraction but also provides a reproducible framework for efficient and consistent verification of depiction errors. This work lays the foundation for applying advanced segmentation techniques to operational digital map inspection and supports the development of scalable quality control systems for national geospatial datasets.

Building segmentation in dense urban scenes remains challenging due to frequent under- segmentation, where adjacent buildings are erroneously merged into single objects. Conventional thresholding, morphological filtering, or context-based optimization methods such as Conditional Random Fields (CRFs) and Graph Cut alleviate this issue only partially, as soft boundaries between closely located buildings often lead to incorrect merging. To address this limitation, we propose a novel post-processing framework termed Local Rank-Based Calibration and Graph Cut for building segmentation refinement. The method introduces a percentile rank-based calibration applied to the softmax probability map before binarization. Instead of treating each pixel’s absolute probability as a decision boundary, our calibration reinterprets the probability as a relative percentile within a local sliding window. Low-percentile pixels are penalized via an exponential weighting function, thereby suppressing spurious foreground responses in narrow gaps between buildings, while high-percentile pixels retain their original values. The calibrated map is subsequently refined using a Graph Cut optimization, which balances unary terms from the calibrated probabilities with pairwise smoothness terms to enforce globally consistent segmentation. Experiments were conducted on high-resolution aerial orthoimages of Suseo, Seoul, using building footprints from the National Geographic Information Institute (NGII) as ground truth. SegFormer was adopted as the baseline segmentation backbone, and multiple post-processing strategies were compared under identical conditions. Quantitative results show that our method reduces the under-segmentation rate from 28.47% (baseline) to 15.33%, while maintaining the lowest over-segmentation rate (0.49%) among all tested methods. Pixel- level metrics also improved, with Intersection over Union (IoU) reaching 0.8012 and F1-score 0.8896. Visual comparisons confirm that the proposed Local Rank-Based Calibration and Graph Cut method effectively separates adjacent buildings while preserving the continuity of individual building interiors. Sensitivity analysis further demonstrates the robustness of the method across a reasonable range of parameter values. Although the Graph Cut step increases computational cost (2 hours 28 minutes for full- scene processing without GPU acceleration), the accuracy gains are significant for applications requiring reliable building-level delineation. The modular design allows our approach to be seamlessly integrated with various backbone models and combined with other post-processing methods such as morphology or CRF. In summary, this study presents a lightweight yet effective refinement strategy that substantially improves building boundary delineation in dense urban imagery. By combining local rank-based calibration with global Graph Cut optimization, the proposed method offers a generalizable and transferable solution for enhancing building segmentation in remote sensing applications.

Maritime search and rescue (SAR) missions require rapid and resource-efficient exploration of wide search areas under severe uncertainty in target location, while actual operational time is highly constrained. To support effective decision-making in such conditions, search planning is commonly formulated as a grid-based coverage path planning problem. However, traditional heuristic- based search patterns used in practice, such as parallel track search and expanding square search, offer limited adaptability because they do not explicitly reflect probability distributions that evolve due to environmental factors such as wind and ocean currents. To address these limitations, this study proposes a maskable Proximal Policy Optimization (PPO) framework for efficient grid-based search, motivated by the operational characteristics of maritime SAR missions. The proposed approach integrates domain- specific action masking rules into the policy optimization process to restrict invalid or inefficient actions during learning and execution. By guiding the agent toward feasible movements and high-priority regions of the search space, the framework promotes structured exploration behavior and stable policy learning in large-scale grid environments with sparse and unevenly distributed targets. The learning environment is constructed to reflect realistic maritime search conditions by incorporating probability distributions derived from drift particle simulations, and the search problem is modeled as a Markov decision process. The proposed method is evaluated under multiple target distribution scenarios and compared with representative heuristic search strategies, including parallel track search, nearest neighbor, expanding square search, and 2-optimization. Search performance is primarily assessed in terms of total search cost, measured by the cumulative movement steps required to complete the search task. Experimental results demonstrate that the maskable PPO consistently achieves the lowest total search cost across all tested environments. In particular, it requires substantially fewer movement steps than parallel track search and nearest neighbor methods, while maintaining comparable or superior efficiency relative to expanding square search and 2-optimization, depending on the target distribution. These results indicate that the proposed approach effectively learns coverage paths that reflect the underlying probability distribution of the environment. Overall, this study demonstrates that action- masking-based reinforcement learning provides a practical and scalable alternative to conventional heuristic search strategies for maritime SAR missions and establishes a foundation for adaptive search planning under realistic environmental uncertainty.

Accurate building representation in national digital maps is essential for ensuring reliable geospatial analyses and supporting policy and administrative decision-making. However, the current quality inspection system in Korea relies on manual sampling-based verification, which inspects only about 30% of each map sheet and therefore risks overlooking errors in the remaining data. In particular, depiction errors in building polygons—such as inaccurate outlines or positional shifts—can significantly degrade the reliability of digital maps, especially when they are used as ground truth for training and validating Artificial Intelligence (AI) models. This study proposes an automated verification framework that combines the complementary strengths of two segmentation approaches: SegFormer, which provides robust contextual awareness for detecting building areas, and Segment Anything Model 2 (SAM 2), which offers precise boundary delineation through prompt-based segmentation. To this end, we designed a context- and boundary-aware segmentation pipeline: SegFormer first identifies candidate building regions from high-resolution true orthoimages, while SAM 2 refines the building outlines at the object level using bounding-box prompts and a probability map derived from both models. This integration resolves under- segmentation issues observed in standalone SegFormer outputs and enables precise extraction of individual building footprints. Experiments were conducted in Seoul using a 2022 true orthoimage (Ground Sample Distance [GSD], 0.12 m) and the 1:5,000 national digital map. The results demonstrated a substantial improvement in segmentation accuracy: the one-to-one matching ratio between building objects increased from 61.46% (SegFormer alone) to 97.56% with the proposed method, while boundary accuracy (Boundary Intersection over Union, BIoU) improved from 65.85% to 72.60%. In depiction error verification, the method achieved 100% recall in detecting erroneous building polygons, ensuring that no actual errors were omitted. Although the precision was relatively low (6.93%) due to false alarms caused by occlusions and resolution limitations, this conservative detection approach offers a practical advantage: only error candidates need to be manually reviewed, reducing the inspection workload by approximately 75% compared to full manual verification. The proposed method highlights the potential of AI-based automation for nationwide digital map quality management. By fusing contextual and boundary-aware segmentation, it not only improves the precision of building footprint extraction but also provides a reproducible framework for efficient and consistent verification of depiction errors. This work lays the foundation for applying advanced segmentation techniques to operational digital map inspection and supports the development of scalable quality control systems for national geospatial datasets.

Building segmentation in dense urban scenes remains challenging due to frequent under- segmentation, where adjacent buildings are erroneously merged into single objects. Conventional thresholding, morphological filtering, or context-based optimization methods such as Conditional Random Fields (CRFs) and Graph Cut alleviate this issue only partially, as soft boundaries between closely located buildings often lead to incorrect merging. To address this limitation, we propose a novel post-processing framework termed Local Rank-Based Calibration and Graph Cut for building segmentation refinement. The method introduces a percentile rank-based calibration applied to the softmax probability map before binarization. Instead of treating each pixel’s absolute probability as a decision boundary, our calibration reinterprets the probability as a relative percentile within a local sliding window. Low-percentile pixels are penalized via an exponential weighting function, thereby suppressing spurious foreground responses in narrow gaps between buildings, while high-percentile pixels retain their original values. The calibrated map is subsequently refined using a Graph Cut optimization, which balances unary terms from the calibrated probabilities with pairwise smoothness terms to enforce globally consistent segmentation. Experiments were conducted on high-resolution aerial orthoimages of Suseo, Seoul, using building footprints from the National Geographic Information Institute (NGII) as ground truth. SegFormer was adopted as the baseline segmentation backbone, and multiple post-processing strategies were compared under identical conditions. Quantitative results show that our method reduces the under-segmentation rate from 28.47% (baseline) to 15.33%, while maintaining the lowest over-segmentation rate (0.49%) among all tested methods. Pixel- level metrics also improved, with Intersection over Union (IoU) reaching 0.8012 and F1-score 0.8896. Visual comparisons confirm that the proposed Local Rank-Based Calibration and Graph Cut method effectively separates adjacent buildings while preserving the continuity of individual building interiors. Sensitivity analysis further demonstrates the robustness of the method across a reasonable range of parameter values. Although the Graph Cut step increases computational cost (2 hours 28 minutes for full- scene processing without GPU acceleration), the accuracy gains are significant for applications requiring reliable building-level delineation. The modular design allows our approach to be seamlessly integrated with various backbone models and combined with other post-processing methods such as morphology or CRF. In summary, this study presents a lightweight yet effective refinement strategy that substantially improves building boundary delineation in dense urban imagery. By combining local rank-based calibration with global Graph Cut optimization, the proposed method offers a generalizable and transferable solution for enhancing building segmentation in remote sensing applications.

Oil spill detection is an important task for protecting and minimizing the harmful effects of oil on the marine ecosystem. Currently, the application of images from unmanned aerial vehicles, along with deep learning, is widely employed. Although these methods have yielded good results, the issue of oil spill classification based on these methods has not received much attention at present. In this research, a deep learning model with a dual attention mechanism consisting of two modules was utilized. The first module focuses on capturing the spatial relationships between each pixel and the entire image, the second module identifies the characteristics between channels in the image, thereby enhancing the ability to detect and classify oil. Additionally, a data augmentation technique based on the Generative Adversarial Networks model was refined and employed to improve the model's accuracy. Experimental results, obtained through comparisons between dataset construction methods, the use of different encoders and decoders, and adjustments hyperparameters, reveal that the best model achieves a mean Intersection over Union by 72.49%. Data augmentation techniques also contribute to a 2.56% increase in mean Intersection over Union. The findings of this research provide a feasible solution not only for detecting but also for classifying oil spills, thereby assisting marine environmental managers in making timely decisions to respond to oil spill accidents.

Abstract. Identifying a distressed vessel among many ships detected in wide-area aerial imagery is a critical challenge in maritime Search and Rescue (SAR) operations. Conventional methods cannot determine which vessel matches the incident description, especially when Automatic Identification System (AIS) reports are uncertain. This study proposes an integrated framework that combines MLLM-based semantic attribute extraction with geolocation fusion to prioritize candidate vessels according to their consistency with Situation Report (SITREP) based scenarios. The method detects vessels using YOLOv8, tracks them with Deep Simple Online and Real-time Tracking (DeepSORT), and performs image-based georeferencing using onboard metadata. A Multi-modal Large Language Model (MLLM) extracts appearance/status attributes from representative vessel images, while scenario descriptions are also converted to attributes. Both sets are encoded using MiniLM embeddings. Finally, semantic similarity is fused with geolocation proximity within an Support Vector Machine (SVM) classifier to produce a probability-ranked list of candidates. Experiments using real aerial search footage demonstrate robust identification performance across a range of scenario quality levels. The correct vessel appears within the top three candidates in more than 73% of cases and within the top five in more than 91%, even when attribute extraction is affected by low resolution, illumination effects, or missing scenario information. These results show that coarse semantic cues, when combined with approximate geolocation, provide a resilient basis for identifying target vessels under high uncertainty. The proposed framework offers a practical foundation for automated SAR decision support, enabling faster and more reliable prioritization during wide-area maritime search operations.

Abstract. Accurate multi-class building change detection in high-resolution aerial imagery is a critical task for urban analysis. However, it is hindered by two key challenges: severe class imbalance and the difficulty of obtaining robust, generalizable feature representations. While recent models show promise, encoders trained from scratch on aerial data remain limited in their representational capacity. Leveraging large-scale Visual Foundation Models (VFMs) offers a path to better features, but full fine-tuning is computationally prohibitive. To address this, we propose Hie-DinoMamba, a novel hierarchical architecture. We integrate a frozen 1.1B parameter DINOv3-L (SAT-493M) encoder, preserving its rich pre-trained knowledge. We efficiently adapt this encoder to the aerial domain using parameter-efficient Low-Rank Adaptation (LoRA). Furthermore, we design a new Hierarchical Mamba FPN decoder that uses Visual State Space Model (VSSM, Mamba) blocks to fuse and refine multi-scale feature pairs in a top-down manner. The model is optimized using a dual-loss strategy (Semantic and Boundary) to ensure both classification accuracy and precise boundary delineation. On the 4-class aerial building change detection benchmark, Hie-DinoMamba achieves state-of-the-art performance with an mIoU of 65.12%, a significant improvement of 2.1 percentage points over the strong VSSM-based baseline (ChangeMamba-MC). Qualitative analysis further demonstrates our model’s superior generalization, successfully detecting complex changes in unseen geographic regions where other models fail.

Abstract. Accurate building change detection depends on how well building boundaries are delineated, as distortions and merging errors hinder reliable correspondence. In dense urban areas, deep learning models frequently merge adjacent buildings—especially within narrow gaps—producing structural inconsistencies that lead to change detection errors. We propose a post-processing method integrating Local Rank-Based Prior Calibration, which reinterprets Softmax probabilities as percentile-based local ranks, with Graph-Cut refinement for structural correction. The refined mask is matched with historical building data to classify four change types. Experiments using aerial imagery from Seoul show that the method reduces structural errors, lowering under-segmentation from 51.64% to 22.02% and improving Intersection over Union (IoU) from 0.748 to 0.759. In change detection, it increases the mean F1-score from 0.522 to 0.608 and improves all classes, including new construction, whose F1-score rises from 0.269 to 0.707. Ablation studies confirm that calibration and graph-based refinement both contribute to the improvements. These results show that stabilizing segmentation outputs enhances the reliability of building-level change detection in dense urban environments.