Hybrid automated UAV target recognition system

David Hung, Kennon McKeever, Ricardo Ramirez, Michael W Marcellin

Research output: Contribution to journalConference article

Abstract

Accurate image classification is one of the core challenges in computer vision. At the annual AUVSI SUAS competition, this challenge is faced in the form of ground target classification from an unmanned aerial vehicle (UAV). Additionally, due to the constraints imposed by the UAV platform, the system design must consider factors such as size, weight, and power consumption. To meet performance requirements while respecting such limitations, the system was broken into two subsystems: an onboard subsystem and a ground based subsystem. This design allows the onboard subsystem, comprised of a DSLR camera and single-board computer, to capture ground target images and perform rudimentary target detection and localization. For further processing and to ultimately classify the targets in each image, data packets are sent to the ground-based subsystem via a 5 GHz wireless link. Convolutional networks are utilized on the ground to achieve state-of-the-art accuracy in classification.

Original languageEnglish (US)
JournalProceedings of the International Telemetering Conference
StatePublished - Jan 1 2017

Fingerprint

pilotless aircraft
target recognition
Unmanned aerial vehicles (UAV)
Image classification
Target tracking
Printed circuit boards
Computer vision
Telecommunication links
Electric power utilization
Cameras
Systems analysis
image classification
computer vision
Processing
systems engineering
platforms
cameras
requirements

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation
  • Computer Networks and Communications
  • Signal Processing

Cite this

Hybrid automated UAV target recognition system. / Hung, David; McKeever, Kennon; Ramirez, Ricardo; Marcellin, Michael W.

In: Proceedings of the International Telemetering Conference, 01.01.2017.

Research output: Contribution to journalConference article

@article{484a080324394092a18d54a68216cb9f,
title = "Hybrid automated UAV target recognition system",
abstract = "Accurate image classification is one of the core challenges in computer vision. At the annual AUVSI SUAS competition, this challenge is faced in the form of ground target classification from an unmanned aerial vehicle (UAV). Additionally, due to the constraints imposed by the UAV platform, the system design must consider factors such as size, weight, and power consumption. To meet performance requirements while respecting such limitations, the system was broken into two subsystems: an onboard subsystem and a ground based subsystem. This design allows the onboard subsystem, comprised of a DSLR camera and single-board computer, to capture ground target images and perform rudimentary target detection and localization. For further processing and to ultimately classify the targets in each image, data packets are sent to the ground-based subsystem via a 5 GHz wireless link. Convolutional networks are utilized on the ground to achieve state-of-the-art accuracy in classification.",
author = "David Hung and Kennon McKeever and Ricardo Ramirez and Marcellin, {Michael W}",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
journal = "Proceedings of the International Telemetering Conference",
issn = "0884-5123",

}

TY - JOUR

T1 - Hybrid automated UAV target recognition system

AU - Hung, David

AU - McKeever, Kennon

AU - Ramirez, Ricardo

AU - Marcellin, Michael W

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Accurate image classification is one of the core challenges in computer vision. At the annual AUVSI SUAS competition, this challenge is faced in the form of ground target classification from an unmanned aerial vehicle (UAV). Additionally, due to the constraints imposed by the UAV platform, the system design must consider factors such as size, weight, and power consumption. To meet performance requirements while respecting such limitations, the system was broken into two subsystems: an onboard subsystem and a ground based subsystem. This design allows the onboard subsystem, comprised of a DSLR camera and single-board computer, to capture ground target images and perform rudimentary target detection and localization. For further processing and to ultimately classify the targets in each image, data packets are sent to the ground-based subsystem via a 5 GHz wireless link. Convolutional networks are utilized on the ground to achieve state-of-the-art accuracy in classification.

AB - Accurate image classification is one of the core challenges in computer vision. At the annual AUVSI SUAS competition, this challenge is faced in the form of ground target classification from an unmanned aerial vehicle (UAV). Additionally, due to the constraints imposed by the UAV platform, the system design must consider factors such as size, weight, and power consumption. To meet performance requirements while respecting such limitations, the system was broken into two subsystems: an onboard subsystem and a ground based subsystem. This design allows the onboard subsystem, comprised of a DSLR camera and single-board computer, to capture ground target images and perform rudimentary target detection and localization. For further processing and to ultimately classify the targets in each image, data packets are sent to the ground-based subsystem via a 5 GHz wireless link. Convolutional networks are utilized on the ground to achieve state-of-the-art accuracy in classification.

UR - http://www.scopus.com/inward/record.url?scp=85041490824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041490824&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85041490824

JO - Proceedings of the International Telemetering Conference

JF - Proceedings of the International Telemetering Conference

SN - 0884-5123

ER -