@InProceedings{RamosCampNasc:2017:SeHyEg,
author = "Ramos, Washington Luis de Souza and Campos, Mario Fernando
Montenegro and Nascimento, Erickson Rangel do",
affiliation = "{Universidade Federal de Minas Gerais (UFMG)} and {Universidade
Federal de Minas Gerais (UFMG)} and {Universidade Federal de Minas
Gerais (UFMG)}",
title = "Semantic Hyperlapse for Egocentric Videos",
booktitle = "Proceedings...",
year = "2017",
editor = "Torchelsen, Rafael Piccin and Nascimento, Erickson Rangel do and
Panozzo, Daniele and Liu, Zicheng and Farias, Myl{\`e}ne and
Viera, Thales and Sacht, Leonardo and Ferreira, Nivan and Comba,
Jo{\~a}o Luiz Dihl and Hirata, Nina and Schiavon Porto, Marcelo
and Vital, Creto and Pagot, Christian Azambuja and Petronetto,
Fabiano and Clua, Esteban and Cardeal, Fl{\'a}vio",
organization = "Conference on Graphics, Patterns and Images, 30. (SIBGRAPI)",
publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
address = "Porto Alegre",
keywords = "Hyperlapse, Fast-forward, Semantic information, First-person
video.",
abstract = "The emergence of low-cost personal mobiles devices and wearable
cameras and, the increasing storage capacity of video-sharing
websites have pushed forward a growing interest towards
first-person videos. Wearable cameras can operate for hours
without the need for continuous handling. These videos are
generally long-running streams with unedited content, which makes
them boring and visually unpalatable since the natural body
movements cause the videos to be jerky and even nauseating.
Hyperlapse algorithms aim to create a shorter watchable version
with no abrupt transitions between the frames. However, an
important aspect of such videos is the relevance of the frames,
usually ignored in hyperlapse videos. In this work, we propose a
novel methodology capable of summarizing and stabilizing
egocentric videos by extracting and analyzing the semantic
information in the frames. This work also describes a dataset
collection with several labeled videos and introduces a new
smoothness evaluation metric for egocentric videos. Several
experiments are conducted to show the superiority of our approach
over the state-of-the-art hyperlapse algorithms as far as semantic
information is concerned. According to the results, our method is
on average 10.67 percentage points higher than the second best in
relation to the maximum amount of semantics that can be obtained,
given the required speed-up. More information can be found in our
supplementary video: https://youtu.be/_TU8KPaA8aU.",
conference-location = "Niter{\'o}i, RJ, Brazil",
conference-year = "17-20 Oct. 2017",
language = "en",
ibi = "8JMKD3MGPAW/3PJJ6JE",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3PJJ6JE",
targetfile = "2017_wtd_sibgrapi.pdf",
urlaccessdate = "2024, Apr. 28"
}