Panorama generation based on aerial images

Jyun Gu Ye, Hua Tsung Chen, W. J. Tsai

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

3 Scopus citations

Abstract

Due to the progress of manufacturing technology of drones and cameras, the prices of camera-equipped drones are not as expensive as ever and can be easily afford by general people. Camera-equipped drones are mainly used for aerial photography, taking pictures from higher positions, and their shooting coverages are usually much larger than those of traditional handheld cameras. In this paper, we propose an aerial panorama generation system using a camera-equipped drone. The aerial scenes along the flight of the drone can be summarized in an aerial panorama. To make the system adaptive to the flying speed of the drone, we propose a novel speed estimation algorithm capable of measuring the distances of pixel movement between consecutive frames. Consequently, the proposed system can generate aerial panoramas properly, in no need of requiring the drone to fly at a constant speed. Experiments conducted on real videos captured by a drone demonstrate that the proposed aerial panorama generation system can produce satisfactory results.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538641958
DOIs
StatePublished - 28 Nov 2018
Event2018 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2018 - San Diego, United States
Duration: 23 Jul 201827 Jul 2018

Publication series

Name2018 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2018

Conference

Conference2018 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2018
CountryUnited States
CitySan Diego
Period23/07/1827/07/18

Keywords

  • Aerial image
  • Aerial panorama
  • Drone
  • Panoramic imagery
  • UAV

Fingerprint Dive into the research topics of 'Panorama generation based on aerial images'. Together they form a unique fingerprint.

Cite this