Detection of loaded and unloaded UAV using deep neural network

Ulzhalgas Seidaliyeva, Manal Alduraibi, Lyazzat Ilipbayeva, Akhan Almagambetov

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

Abstract

Unmanned aerial vehicles or drones quickly became cheaper, becoming more advanced and affordable to the general public. And the ease of control made them popular among people, who want to deliver various suspicious loads. UAV detection can be performed by different existing techniques, such as radar, radio frequency, acoustic and optical sensing techniques. Because of low-cost and low-power technology computer vision is considered as an effective method for detecting Unmanned aerial vehicles. Previous studies of UAV detection mostly have dealt with detection of UAV existence. The primary aim of this paper is to review recent research into the UAV detection and perform single stage loaded and unloaded UAV detection based on YOLOv2.
Original languageEnglish
Title of host publication2020 Fourth IEEE International Conference on Robotic Computing (IRC)
Pages490-494
Number of pages5
DOIs
Publication statusPublished - Nov 1 2020

Keywords

  • Visualization
  • Radar detection
  • Phantoms
  • Detectors
  • Unmanned aerial vehicles
  • Optical sensors
  • Payloads
  • UAV detection
  • computer vision
  • YOLOv2
  • deep learning

Fingerprint

Dive into the research topics of 'Detection of loaded and unloaded UAV using deep neural network'. Together they form a unique fingerprint.

Cite this