Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Real-Time Fast Unmanned Aerial Vehicle Detection Using Dynamic Vision Sensors

Jakub Mandula, Jonas Kühne, Luca Pascarella, Michele Magno

TL;DR

This paper presents F-UAV-D (Fast Unmanned Aerial Vehicle Detector), an embedded system that enables fast-moving drone detection and proposes a setup to exploit DVS as an alternative to RGB cameras in a real-time and low-power configuration.

Abstract

Unmanned Aerial Vehicles (UAVs) are gaining popularity in civil and military applications. However, uncontrolled access to restricted areas threatens privacy and security. Thus, prevention and detection of UAVs are pivotal to guarantee confidentiality and safety. Although active scanning, mainly based on radars, is one of the most accurate technologies, it can be expensive and less versatile than passive inspections, e.g., object recognition. Dynamic vision sensors (DVS) are bio-inspired event-based vision models that leverage timestamped pixel-level brightness changes in fast-moving scenes that adapt well to low-latency object detection. This paper presents F-UAV-D (Fast Unmanned Aerial Vehicle Detector), an embedded system that enables fast-moving drone detection. In particular, we propose a setup to exploit DVS as an alternative to RGB cameras in a real-time and low-power configuration. Our approach leverages the high-dynamic range (HDR) and background suppression of DVS and, when trained with various fast-moving drones, outperforms RGB input in suboptimal ambient conditions such as low illumination and fast-moving scenes. Our results show that F-UAV-D can (i) detect drones by using less than <15 W on average and (ii) perform real-time inference (i.e., <50 ms) by leveraging the CPU and GPU nodes of our edge computer.

Towards Real-Time Fast Unmanned Aerial Vehicle Detection Using Dynamic Vision Sensors

TL;DR

This paper presents F-UAV-D (Fast Unmanned Aerial Vehicle Detector), an embedded system that enables fast-moving drone detection and proposes a setup to exploit DVS as an alternative to RGB cameras in a real-time and low-power configuration.

Abstract

Unmanned Aerial Vehicles (UAVs) are gaining popularity in civil and military applications. However, uncontrolled access to restricted areas threatens privacy and security. Thus, prevention and detection of UAVs are pivotal to guarantee confidentiality and safety. Although active scanning, mainly based on radars, is one of the most accurate technologies, it can be expensive and less versatile than passive inspections, e.g., object recognition. Dynamic vision sensors (DVS) are bio-inspired event-based vision models that leverage timestamped pixel-level brightness changes in fast-moving scenes that adapt well to low-latency object detection. This paper presents F-UAV-D (Fast Unmanned Aerial Vehicle Detector), an embedded system that enables fast-moving drone detection. In particular, we propose a setup to exploit DVS as an alternative to RGB cameras in a real-time and low-power configuration. Our approach leverages the high-dynamic range (HDR) and background suppression of DVS and, when trained with various fast-moving drones, outperforms RGB input in suboptimal ambient conditions such as low illumination and fast-moving scenes. Our results show that F-UAV-D can (i) detect drones by using less than <15 W on average and (ii) perform real-time inference (i.e., <50 ms) by leveraging the CPU and GPU nodes of our edge computer.
Paper Structure (12 sections, 6 figures, 1 table)

This paper contains 12 sections, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Overview
  4. Hardware
  5. Software
  6. Methodology
  7. Dataset Labeling
  8. Event-to-Frame Conversion
  9. Camera Synchronization and Calibration
  10. Data Collection
  11. Results
  12. Conclusion and Future Work

Figures (6)

  • Figure 1: Overview of the system. The solid boxes and show the hardware components and the dashed boxes and illustrate the software parts.
  • Figure 2: Selected image sensors and computational unit.
  • Figure 3: An example of RGB and event-to-frame overlapping.
  • Figure 4: AprilTag grid in RGB and event-to-frame view.
  • Figure 5: Power consumption during real-time inference. For batch sizes $B=1$, $B=2$, and $B=16$
  • ...and 1 more figures