UAVDB: Trajectory-Guided Adaptable Bounding Boxes for UAV Detection

2024-09-09

arXiv.org

AI Summary

Existing UAV detection datasets suffer from limited scale and coarse annotations, hindering model robustness and long-range small-object detection performance. To address this, we introduce UAVDB—the first high-resolution, cross-scale comprehensive UAV detection benchmark. We further propose Trajectory-based Patch Intensity Convergence (PIC), a novel automatic annotation method that generates high-fidelity, scale-adaptive bounding boxes without human intervention. Experiments demonstrate that PIC achieves significantly higher annotation accuracy than both manual and semi-automatic approaches, while also offering superior inference efficiency. When evaluated on mainstream detectors—including YOLOv5, YOLOv8, and YOLOv10—UAVDB substantially improves detection performance for UAVs as small as a single pixel and as distant as kilometer-range targets. This work establishes a new standard for long-range, high-resolution UAV detection.

Technology Category

• Computer Vision: Object Detection & Categorization
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The widespread deployment of Unmanned Aerial Vehicles (UAVs) in surveillance, security, and airspace management has created an urgent demand for precise, scalable, and efficient UAV detection. However, existing datasets often suffer from limited scale diversity and inaccurate annotations, hindering robust model development. This paper introduces UAVDB, a high-resolution UAV detection dataset constructed using Patch Intensity Convergence (PIC). This novel technique automatically generates high-fidelity bounding box annotations from UAV trajectory data~cite{li2020reconstruction}, eliminating the need for manual labeling. UAVDB features single-class annotations with a fixed-camera setup and consists of RGB frames capturing UAVs across various scales, from large-scale UAVs to near-single-pixel representations, along with challenging backgrounds that pose difficulties for modern detectors. We first validate the accuracy and efficiency of PIC-generated bounding boxes by comparing Intersection over Union (IoU) performance and runtime against alternative annotation methods, demonstrating that PIC achieves higher annotation accuracy while being more efficient. Subsequently, we benchmark UAVDB using state-of-the-art (SOTA) YOLO-series detectors, establishing UAVDB as a valuable resource for advancing long-range and high-resolution UAV detection.

Problem

• Precise UAV detection in surveillance
• Scalable dataset for UAV detection
• Efficient bounding box annotation method

Innovation

• Patch Intensity Convergence technique
• Automated high-fidelity bounding boxes
• Large-scale single-class UAV dataset