UAVDB: Point-Guided Masks for UAV Detection and Segmentation

TL;DR

UAVDB is a new benchmark dataset for UAV detection and segmentation, created with a novel point-guided annotation method that reduces manual labeling and enhances multi-scale UAV analysis.

Contribution

The paper introduces UAVDB, a large-scale UAV dataset with point-guided weak supervision annotations and segmentation masks, enabling improved detection and segmentation research.

Findings

PIC annotation method outperforms existing techniques in IoU.

UAVDB captures UAVs across a wide scale range, including near single-pixel objects.

Benchmark results establish baselines for YOLO detectors on UAVDB.

Abstract

Accurate detection of Unmanned Aerial Vehicles (UAVs) is critical for surveillance, security, and airspace monitoring. However, existing datasets remain limited in scale, resolution, and the ability to capture objects across extreme size variations. To address these challenges, we present UAVDB, a benchmark dataset for UAV detection and segmentation, constructed via a point-guided weak supervision pipeline. We introduce Patch Intensity Convergence (PIC), a lightweight annotation method that converts trajectory points into bounding boxes, eliminating the need for manual labeling while preserving precise spatial localization. Building upon these annotations, we further generate segmentation masks using SAM2, enriching the dataset with multi-task labels. UAVDB consists of RGB frames from a fixed-camera multi-view video dataset, capturing UAVs across scales ranging from clearly visible objects to near single-pixel instances under diverse conditions. Quantitative results show that PIC combined with SAM2 outperforms existing annotation techniques in terms of IoU. Furthermore, we benchmark YOLO-based detectors on UAVDB, establishing baselines for future research.