Seraphim Drone Detection: Images from 23 Open-Source Datasets

Encompassing images for training object detection models to identify drones, primarily rotary-wing UAVs, in various environments. It was curated from 23 open-source datasets and processed through a custom cleaning pipeline. The author is lgrzybowski, and it was last updated in December 2025.

Use Cases

• Train an object detection model to identify rotary-wing drones in diverse environmental conditions.
• Fine-tune a model to distinguish between rotary-wing, fixed-wing, and hybrid UAVs in images.
• Benchmark detection performance on drone images aggregated from multiple open-source datasets.

Strengths

• Aggregated from 23 distinct open-source datasets, providing a broad base of source imagery.
• Processed through a custom cleaning pipeline designed for object detection tasks.
• Focuses on drone detection, a specific computer vision application for aerial surveillance.

Limitations

• Specific counts for images, annotations, and class distributions are unknown.
• The dataset's composition and potential class imbalance between rotary-wing and other drone types are not detailed.
• The geographic and temporal coverage of the source images is unspecified.

Provenance

Source

Curated from 23 open-source datasets.

Collection Method

Aggregated and processed through a custom cleaning pipeline.

Freshness

Last updated on 2025-12-03.