Multi-Drone based Single Object Tracking with Agent Sharing Network

TL;DR

This paper introduces a new multi-drone dataset and a novel agent sharing network that enhances single object tracking accuracy by leveraging multiple drones and self-supervised template sharing.

Contribution

The paper presents a new multi-drone dataset, specialized evaluation metrics, and a novel agent sharing network for improved multi-drone object tracking.

Findings

ASNet outperforms recent state-of-the-art trackers.

New MDOT dataset with high-resolution drone footage.

Designed metrics AFS and IFS for multi-drone tracking evaluation.

Abstract

Drone equipped with cameras can dynamically track the target in the air from a broader view compared with static cameras or moving sensors over the ground. However, it is still challenging to accurately track the target using a single drone due to several factors such as appearance variations and severe occlusions. In this paper, we collect a new Multi-Drone single Object Tracking (MDOT) dataset that consists of 92 groups of video clips with 113,918 high resolution frames taken by two drones and 63 groups of video clips with 145,875 high resolution frames taken by three drones. Besides, two evaluation metrics are specially designed for multi-drone single object tracking, i.e. automatic fusion score (AFS) and ideal fusion score (IFS). Moreover, an agent sharing network (ASNet) is proposed by self-supervised template sharing and view-aware fusion of the target from multiple drones, which can improve the tracking accuracy significantly compared with single drone tracking. Extensive experiments on MDOT show that our ASNet significantly outperforms recent state-of-the-art trackers.