Uncertainty Quantification-Based Unmanned Aircraft System Detection using Deep Ensembles

Rajeev Sahay, Gabriel C. Birch, Jaclynn J. Stubbs, Christopher G. Brinton

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Robust and accurate unmanned aircraft system (UAS) detection is pivotal in restricted air spaces. Deep learning-based object detection has been proposed to identify the presence of UASs, but it introduces two key challenges. Specifically, deep learning detectors (i) provide point estimates at test-time with no associated measure of uncertainty, and (ii) easily trigger false positive detections for birds and other aerial wildlife. In this work, we propose a novel detection algorithm, which is capable of providing uncertainty quantification (UQ) metrics at test time while also significantly reducing the false positive rate on natural wildlife. Our proposed method consists of using an ensemble of object detectors to generate a distributive estimate of each input prediction. In addition, we measure multiple UQ-based scoring metrics for each input to further validate our model's effectiveness. Through evaluation on our custom generated UAS dataset, consisting of images captured from deployed cameras, we show that our model provides robust UQ estimates, low false positive rates on wildlife, and significantly improved error rates over singular deep learning detection models.

Original languageEnglish (US)
Title of host publication2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665482431
DOIs
StatePublished - 2022
Externally publishedYes
Event95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring - Helsinki, Finland
Duration: Jun 19 2022Jun 22 2022

Publication series

NameIEEE Vehicular Technology Conference
Volume2022-June
ISSN (Print)1550-2252

Conference

Conference95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring
Country/TerritoryFinland
CityHelsinki
Period6/19/226/22/22

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics

Keywords

  • Deep learning
  • UAS detection
  • multispectral image processing
  • object detection
  • uncertainty quantification

Fingerprint

Dive into the research topics of 'Uncertainty Quantification-Based Unmanned Aircraft System Detection using Deep Ensembles'. Together they form a unique fingerprint.

Cite this