A Deep Learning Approach to Drone Monitoring

TL;DR

This paper introduces a deep learning-based drone monitoring system that uses synthetic data augmentation and residual tracking to effectively detect and track small drones in complex environments, outperforming individual modules.

Contribution

It presents a novel model-based drone augmentation technique and an integrated detection and tracking system trained on synthetic data for real-world drone monitoring.

Findings

System performs well on real-world images with complex backgrounds.

Synthetic data training achieves competitive detection and tracking accuracy.

Proposed method outperforms standalone detection or tracking modules.

Abstract

A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work. The biggest challenge in adopting deep learning methods for drone detection is the limited amount of training drone images. To address this issue, we develop a model-based drone augmentation technique that automatically generates drone images with a bounding box label on drone's location. To track a small flying drone, we utilize the residual information between consecutive image frames. Finally, we present an integrated detection and tracking system that outperforms the performance of each individual module containing detection or tracking only. The experiments show that, even being trained on synthetic data, the proposed system performs well on real world drone images with complex background. The USC drone detection and tracking dataset with user labeled bounding boxes is available to the public.