Multi-Domain Network Performance Analysis for Vehicle Tracking in Aerial Video

Oliver Sumari H. Felix, Carlos Gutierrez C. Juan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The Drone is an unmanned aerial vehicle widely used to take pictures and record videos at high altitude, recording information for applications such as video surveillance, to be able to detect cars and people in real time, the main problem is that both the drone as objects are move, this make difficult the track objects with traditional techniques. Faced this problem, the present research proposes the use of convolutional neural network with multidomain learning (MDNet) and camera movement models for the detection and monitoring of cars based on aerial videos. The propouse obtaining very good results in compare with traditional methods, obtaining a 90 % of success in object tracking, which is useful for practical applications.

Original languageEnglish
Title of host publication2020 39th International Conference of the Chilean Computer Science Society, SCCC 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728183282
DOIs
StatePublished - 16 Nov 2020
Event39th International Conference of the Chilean Computer Science Society, SCCC 2020 - Coquimbo, Chile
Duration: 16 Nov 202020 Nov 2020

Publication series

NameProceedings - International Conference of the Chilean Computer Science Society, SCCC
Volume2020-November
ISSN (Print)1522-4902

Conference

Conference39th International Conference of the Chilean Computer Science Society, SCCC 2020
Country/TerritoryChile
CityCoquimbo
Period16/11/2020/11/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

  • MDNet
  • Multidomain learning
  • Object tracking

Fingerprint

Dive into the research topics of 'Multi-Domain Network Performance Analysis for Vehicle Tracking in Aerial Video'. Together they form a unique fingerprint.

Cite this