Coastal debris is a global environmental issue that requires systematic monitoring strategies based on reliable statistical data. Recent advances in remote sensing and deep learning-based object detection have enabled the development of efficient coastal debris monitoring systems. In this study, two state-of-the-art object detection models—RT-DETR and YOLOv10—were applied to UAV-acquired images for coastal debris detection. Their false positive characteristics were analyzed to provide guidance on model selection under different coastal environmental conditions. Quantitative evaluation using mean average precision (mAP@0.5) showed comparable performance between the two models (RT-DETR: 0.945, YOLOv10: 0.957). However, bounding box label accuracy revealed a significant gap, with RT-DETR achieving 80.18% and YOLOv10 only 53.74%. Class-specific analysis indicated that both models failed to detect Metal and Glass and showed low accuracy for fragmented debris, while buoy-type objects with high structural integrity (Styrofoam Buoy, Plastic Buoy) were consistently identified. Error analysis further revealed that RT-DETR tended to overgeneralize by misclassifying untrained objects as similar classes, whereas YOLOv10 exhibited pronounced intra-class confusion in fragment-type objects. These findings demonstrate that mAP alone is insufficient to evaluate model performance in real-world coastal monitoring. Instead, model assessment should account for training data balance, coastal environmental characteristics, and UAV imaging conditions. Future studies should incorporate diverse coastal environments and apply dataset augmentation to establish statistically robust and standardized monitoring protocols for coastal debris.

Ocean color remote sensing provides continuous observations of marine environments, with the Geostationary Ocean Color Imager-II (GOCI-II) offering high temporal resolution data for waters surrounding the Korean Peninsula. However, cloud cover and atmospheric interference frequently create data gaps that compromise the continuity and reliability of chlorophyll-a concentration measurements—a critical indicator of marine ecosystem health. This study proposes the Spatiotemporal Attention Partial Convolution model to reconstruct missing chlorophyll-a values in multi-day satellite imagery. The model extends two-dimensional partial convolution to three dimensions, enabling simultaneous exploration of spatial patterns and temporal dynamics. A 3D attention mechanism guides the network to focus on informative spatiotemporal features during reconstruction. To ensure robust training, we developed a comprehensive artificial cloud mask generation strategy using Gaussian Random Fields with parameterized Cloud Density Index and Missing Pixel Ratio, creating diverse missing data scenarios that exceed the variability found in observational data alone. Rigorous evaluation using actual GOCI-II cloud masks from 2024 was conducted to evaluate performance across varying missing data conditions, achieving mean absolute error of 0.036 mg/m³, root mean squared error of 0.068 mg/m³, and R² of 0.865. Long-term spatiotemporal consistency analysis across ten selected regions showed substantial improvements in spatial and temporal data coverage, with valid pixels increasing from 54% to 97%. Qualitative assessments confirmed that reconstructed images preserve natural spatial continuity without artifacts, significantly enhancing the practical utility of GOCI-II data for marine environmental monitoring and research applications requiring high temporal resolution.

Bo-Ram Kim, Ye-Been Do, Jun-Hwa Chi, Tae-Hoon Kim. Korean J. Remote Sens. 2025;41:327-39. https://doi.org/10.7780/kjrs.2025.41.2.1.7

As problems regarding the impact of marine debris on the marine environment emerge, research is being conducted to address the management of various types of marine debris, including coastal, floating, and sedimentation. In the case of Korea, which has a peninsula-shaped topography surrounded by the sea on three sides, significant damage from coastal debris occurs every year, and a national-level management plan is being prepared for this. Recently, to investigate the various types of beaches in Korea, coastal debris surveys using remote sensing devices such as UAV, CCTV, satellites, and mobile devices are being conducted. However, unlike human surveys where clear standards for coastal debris surveys using remote sensing devices are defined, research is needed to establish uniform standards. Therefore, in this study, we examined the optimal coastal debris survey method for each device and the application of artificial intelligence for automated recognition to establish the consistency of coastal debris survey methods using remote sensing devices and the validity of survey standards. The research method involved analyzing guidelines and previous research cases and applying visual intelligence using data collected from actual sea areas. First, we decided to use UAV, CCTV, and mobile devices for coastal debris investigation and research using existing marine debris monitoring guidelines, and derived data collection methods for each device by referencing the human-collected coastal debris investigation method. Additionally, for the analysis of previous research cases, a meta-analysis was performed using the above research papers on coastal debris using remote sensing devices, and trends in the field of coastal debris investigation by device were confirmed. In addition, coastal debris data were collected using remote sensing devices in various actual sea areas (stones, plants, sand, etc.) to qualitatively confirm the degree of object recognition and confirm differences by geographical characteristics of the coastal. Lastly, artificial intelligence provided visual information. We conducted a review of automated recognition methods other than human-eye recognition by applying it to the field of visual intelligence that uses information delivered using. Finally, we verified the unique characteristics of each remote sensing device, such as spatial resolution and available time, and extracted information such as the size that can recognize objects and the degree of color recognition. We also extracted coastal debris suitable for the device, such as the number of survey personnel required, monitoring cycle, and suitable target waters. Monitoring considerations were derived. By combining coastal debris survey considerations, we proposed criteria for coastal debris surveys, including device selection according to survey purpose and data collection methods for each device according to survey method, and used the proposed standards to collect coastal debris survey data using visual intelligence. As a result of its application, it had a positive impact. The results of this study are meaningful in suggesting guidelines for selecting a survey method according to Korean coastal areas with diverse geographical characteristics and debris distribution, and are expected to be helpful in supporting various decision-making for coastal surveys.

Recent studies have increasingly utilized drones for remote sensing, driven by the widespread distribution of marine debris along coastal areas. When monitoring coastal debris using drones, flight altitude is a critical factor that directly impacts both the quality of image data and the monitoring duration. However, designing monitoring systems based solely on altitude may lead to variations in spatial resolution (GSD) caused by differences in camera specifications across various drone models. Such variations in GSD levels impact the interpretability of debris within the imagery. This study evaluates the interpretability of coastal debris at different GSD levels determined by drone specifications and flight altitudes. Based on prior studies, we collected data at four altitudes by GSD: 18.6 m (GSD: 0.5 cm/pixel), 27.9 m (GSD: 0.75 cm/pixel), 37.2 m (GSD: 1.0 cm/pixel), and 46.5 m (GSD: 1.25 cm/pixel). Coastal debris types were categorized into eight classes, defined based on the top 10 most frequently identified debris types over a four-year period in Korea. We also assessed the quality and interpretability of coastal debris data under varying spatial resolutions of drone imagery, with a particular focus on the eight defined categories. Interpretability was assessed based on the National Image Interpretability Rating Scales (NIIRS), developed by Image Intelligence, which defines four interpretability levels: I (Identify), B (Distinguish), D (Detect), and N (Not Detect). The results demonstrated that the interpretability of coastal debris varies depending on debris type, color, and size with changes in GSD. Furthermore, the detectable categories of debris were defined for each GSD level. Through this study, it is expected to support decisions on appropriate GSD settings and monitoring methods for different coastal debris survey objectives and conditions. The findings may also help in developing national policies for managing coastal debris.