Abstract

This paper presents an asynchronous event-based scheme for automatic intrusion monitoring using Unmanned Aerial Systems (UAS). Event cameras are neuromorphic sensors that capture the illumination changes in the camera pixels with high temporal resolution and dynamic range. In contrast to conventional frame-based cameras, they are naturally robust against motion blur and lighting conditions, which make them ideal for outdoor aerial robot applications. The presented scheme includes two main perception components. First, an asynchronous event-based processing system efficiently detects intrusions by combining several asynchronous event-based algorithms that exploit the advantages of the sequential nature of the event stream. The second is an off-line training mechanism that adjusts the parameters of the event-based algorithms to a particular surveillance scenario and mission. The proposed perception system was implemented in ROS for on-line execution on board UAS, integrated in an autonomous aerial robot architecture, and extensively validated in challenging scenarios with a wide variety of lighting conditions, including day and night experiments in pitch dark conditions.

Highlights

  • Unmanned Aerial Systems (UAS) have attracted high interest in large-area surveillance and monitoring applications

  • This paper presents an asynchronous event-based processing scheme for intrusion monitoring with UAS

  • WORK This paper proposes an event-based processing scheme for intrusion monitoring with UAS

Read more

Summary

INTRODUCTION

Unmanned Aerial Systems (UAS) have attracted high interest in large-area surveillance and monitoring applications. Event images enable designing elaborated frame-based processing schemes, but they cannot always fully exploit the sequential and asynchronous capabilities of the event cameras. This paper presents an asynchronous event-based processing scheme for intrusion monitoring with UAS. The main improvements over [7] are: (i) a new auto-tuning system for adapting the parameters of the intrusion monitoring scheme to a particular surveillance scenario; (ii) robustness improvement in the event-based corner detection, tracking, and clustering algorithms of the intrusion monitoring scheme; (iii) development, integration, and validation of the proposed scheme in an aerial robot architecture for autonomous surveillance; and (iv) new experimental validation in challenging scenarios and robustness evaluation against lighting conditions.

STATE OF THE ART
ATTENTION FOCUS FOR ASYNCHRONOUS EVENT-BASED VISION
EXPERIMENTAL VALIDATION AND ANALYSIS
PERFORMANCE EVALUATION
Findings
CONCLUSION AND FUTURE WORK
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call