Global-Local MAV Detection under Challenging Conditions based on Appearance and Motion

TL;DR

This paper introduces a global-local MAV detection method that fuses appearance and motion features, improving accuracy and efficiency in challenging scenarios, and demonstrates near real-time performance on embedded hardware.

Contribution

The paper presents a novel global-local MAV detector that combines appearance and motion cues with an adaptive switching mechanism, along with a new challenging dataset.

Findings

Outperforms state-of-the-art methods in accuracy

Operates near real-time on NVIDIA Jetson NX Xavier

Effective in complex backgrounds and small target detection

Abstract

Visual detection of micro aerial vehicles (MAVs) has received increasing research attention in recent years due to its importance in many applications. However, the existing approaches based on either appearance or motion features of MAVs still face challenges when the background is complex, the MAV target is small, or the computation resource is limited. In this paper, we propose a global-local MAV detector that can fuse both motion and appearance features for MAV detection under challenging conditions. This detector first searches MAV target using a global detector and then switches to a local detector which works in an adaptive search region to enhance accuracy and efficiency. Additionally, a detector switcher is applied to coordinate the global and local detectors. A new dataset is created to train and verify the effectiveness of the proposed detector. This dataset contains more challenging scenarios that can occur in practice. Extensive experiments on three challenging datasets show that the proposed detector outperforms the state-of-the-art ones in terms of detection accuracy and computational efficiency. In particular, this detector can run with near real-time frame rate on NVIDIA Jetson NX Xavier, which demonstrates the usefulness of our approach for real-world applications. The dataset is available at https://github.com/WestlakeIntelligentRobotics/GLAD. In addition, A video summarizing this work is available at https://youtu.be/Tv473mAzHbU.