Skip to main navigation Skip to search Skip to main content

A monocular vision localization algorithm based on maximum likelihood estimation

  • Harbin Institute of Technology Shenzhen

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

Abstract

In this paper, we present a method that uses the theory of maximum likelihood estimation to improve the precision of the unmanned aerial vehicle (UAV) localization algorithm based on monocular vision. The main goal of this work is to obtain the accurate position information of UAV and achieve the autonomous navigation in complex indoor and outdoor environments. An embedded camera mounted on the UAV platform is used to provide real-time video streams to the vision-based localization algorithm. All the algorithms run in the onboard computer to ensure the real-time property of the system. Simulation of the UAV platform with monocular camera is performed to verify the feasibility of the improved localization algorithm firstly. After the simulation verification, a series of real-time experiments are implemented to demonstrate the precision of the algorithm.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages561-566
Number of pages6
ISBN (Electronic)9781538620342
DOIs
StatePublished - 2 Jul 2017
Externally publishedYes
Event2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017 - Okinawa, Japan
Duration: 14 Jul 201718 Jul 2017

Publication series

Name2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
Volume2017-July

Conference

Conference2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
Country/TerritoryJapan
CityOkinawa
Period14/07/1718/07/17

Fingerprint

Dive into the research topics of 'A monocular vision localization algorithm based on maximum likelihood estimation'. Together they form a unique fingerprint.

Cite this