Towards Unsupervised Familiar Scene Recognition in Egocentric Videos

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

Abstract

Nowadays, there is an upsurge of interest in using lifelogging devices. Such devices generate huge amounts of image data; consequently, the need for automatic methods for analyzing and summarizing these data is drastically increasing. We present a new method for familiar scene recognition in egocentric videos, based on background pattern detection through automatically configurable COSFIRE filters. We present some experiments over egocentric data acquired with the Narrative Clip.
Original languageEnglish
Title of host publicationAutonomous Systems 2015 - Proceedings of the 8th GI Conference
PublisherVDI Verlag
Pages80-91
Number of pages11
ISBN (Print)978-3-18-384210-0
Publication statusPublished - 2015
EventAutonomous Systems 2015-the 8th GI Conference - Hotel Sabina Playa C/ Es Rafal nº 4,07560, Cala Millor, Spain
Duration: 25-Oct-201530-Oct-2015

Publication series

NameFortschritt-Berichte VDI. Informatik/Kommunikationstechnik
Number0178-9627
Volume842

Conference

ConferenceAutonomous Systems 2015-the 8th GI Conference
CountrySpain
CityCala Millor
Period25/10/201530/10/2015

Keywords

  • lifelogging
  • ego-centric vision
  • scene recognition

Cite this