Operationalizing Maritime Intelligence with Scalable Vessel Detection Datasets

About the customer

A leading geospatial analytics company leverages AI and satellite data to deliver actionable insights for global enterprises and governments. Their advanced platform transforms massive datasets-including satellite imagery, mobile signals, and IoT feeds-into clear, predictive intelligence that drives operational efficiency and strategic advantage. From infrastructure monitoring and supply chain visibility to population movement analysis, they enable faster, data-driven decision-making across industries, enhancing agility and real-world responsiveness.

Goals

To deliver high-quality, consistent ground truth annotations using 50 cm resolution electro-optical satellite imagery, enabling the development of a high-performance multiclass vessel object detection model. The objective was to accelerate AI model development and deployment through fast turnaround, rigorous quality control, and cost-efficient labeling reducing time-to-production and improving model accuracy at scale.

Challenge

With distinct vessel classes to be labeled across several hundred square kilometers of scenes, developing a high-performance object detection model demands precise annotations and meticulous attention to detail. The complexity of this task is amplified by the diversity of vessel types, environmental conditions, and geospatial contexts present in the 50cm resolution remote sensing imagery. Achieving high-quality, consistent labeling is critical to model accuracy and robustness. The primary challenges involve managing occlusions from nearby docked vessels, variations in vessel orientation, a wide range of vessel attributes, and visually similar non-vessel objects. Precise polygon-based annotations are required, with strict attention to avoiding label overlaps between adjacent objects to ensure clarity and maintain annotation integrity in complex maritime scenes.

Solution

Labelbees provided end-to-end data annotation through its human-in-the-loop pipeline, combining Labelbees’ ontology knowledge base, expert annotators, custom workflows, and robust quality control. The team delivered hundreds of thousands of labeled assets within weeks, enabling the client to accelerate model training and reduce development time. Labelbees developed a comprehensive ontology covering over 100,000 vessels globally. The ontology is structured into 6 Level 1 categories and 37 Level 2 subcategories and incorporates deep domain knowledge of target objects and their attributes.

To tackle project complexities, our in-house labeling team leveraged subject matter experts, ML data specialists, and data scientists, ensuring high-quality outcomes throughout the pipeline. By adhering to a rigorous, custom-built data labeling workflow, Labelbees delivered a tailored solution that included:

• Ontology Development & Review
• Edge Case Identification & Curation
• Custom Metadata Collection
• Detailed Labeling Guidelines & Documentation
• Specialized Labeling Strategies per Class
• Robust Quality Assurance Process
• Iterative Feedback Loop
• Dataset Insights & Reporting

Result

Labelbees' expertise in high-quality annotation contributed to the success of a state-of-the-art multiclass vessel object detection model. The models achieved superior detection performance by ensuring precise and consistent labeling, making them more effective for several use cases, such as traffic management, urban planning, environmental monitoring, air pollution assessment, and economic analysis applications.

In our work, we enabled our customer with faster deployment of AI features by significantly improving internal efficiency across their machine learning pipelines.

• Achieved near-instant labeling delivery, cutting annotation cycles from 14 days to under a day
• Consistent 10-15% boost in annotation efficiency
• Avoided costly rework and delays
• Achieved first-pass approval
• Faster deployment of AI features to customers
• Reduced model iteration cycles
• Competitive edge in time-sensitive markets
• Improved internal efficiency across the ML pipelines