Viewing Experience Model of First-Person Videos

First-Person Videos (FPVs) are recorded using wearable cameras to share the recorder’s First-Person Experience (FPE). Ideally, the FPE is conveyed by the viewing experience of the FPV. However, raw FPVs are usually too shaky to watch, which ruins the viewing experience. To solve this probl...

Full description

Bibliographic Details
Main Authors: Biao Ma, Amy R. Reibman
Format: Article
Language:English
Published: MDPI AG 2018-08-01
Series:Journal of Imaging
Subjects:
Online Access:http://www.mdpi.com/2313-433X/4/9/106
id doaj-16a8e5537eea4b0b83f0fc5fa4e90b93
record_format Article
spelling doaj-16a8e5537eea4b0b83f0fc5fa4e90b932020-11-24T21:27:21ZengMDPI AGJournal of Imaging2313-433X2018-08-014910610.3390/jimaging4090106jimaging4090106Viewing Experience Model of First-Person VideosBiao Ma0Amy R. Reibman1School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USASchool of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USAFirst-Person Videos (FPVs) are recorded using wearable cameras to share the recorder’s First-Person Experience (FPE). Ideally, the FPE is conveyed by the viewing experience of the FPV. However, raw FPVs are usually too shaky to watch, which ruins the viewing experience. To solve this problem, we improve the viewing experience of FPVs by modeling it as two parts: video stability and First-Person Motion Information (FPMI). Existing video stabilization techniques can improve the video stability but damage the FPMI. We propose a Viewing Experience (VE) score, which measures both the stability and the FPMI of a FPV by exploring the mechanism of human perception. This enables us to further develop a system that can stabilize FPVs while preserving their FPMI so that the viewing experience of FPVs is improved. Objective tests show that our measurement is robust under different kinds of noise, and our system has competitive performance relative to current stabilization techniques. Subjective tests show that (1) both our stability and FPMI measurements can correctly compare the corresponding attributes of an FPV across different versions of the same content, and (2) our video processing system can effectively improve the viewing experience of FPVs.http://www.mdpi.com/2313-433X/4/9/106First-Person Videosviewing experiencevideo stabilization
collection DOAJ
language English
format Article
sources DOAJ
author Biao Ma
Amy R. Reibman
spellingShingle Biao Ma
Amy R. Reibman
Viewing Experience Model of First-Person Videos
Journal of Imaging
First-Person Videos
viewing experience
video stabilization
author_facet Biao Ma
Amy R. Reibman
author_sort Biao Ma
title Viewing Experience Model of First-Person Videos
title_short Viewing Experience Model of First-Person Videos
title_full Viewing Experience Model of First-Person Videos
title_fullStr Viewing Experience Model of First-Person Videos
title_full_unstemmed Viewing Experience Model of First-Person Videos
title_sort viewing experience model of first-person videos
publisher MDPI AG
series Journal of Imaging
issn 2313-433X
publishDate 2018-08-01
description First-Person Videos (FPVs) are recorded using wearable cameras to share the recorder’s First-Person Experience (FPE). Ideally, the FPE is conveyed by the viewing experience of the FPV. However, raw FPVs are usually too shaky to watch, which ruins the viewing experience. To solve this problem, we improve the viewing experience of FPVs by modeling it as two parts: video stability and First-Person Motion Information (FPMI). Existing video stabilization techniques can improve the video stability but damage the FPMI. We propose a Viewing Experience (VE) score, which measures both the stability and the FPMI of a FPV by exploring the mechanism of human perception. This enables us to further develop a system that can stabilize FPVs while preserving their FPMI so that the viewing experience of FPVs is improved. Objective tests show that our measurement is robust under different kinds of noise, and our system has competitive performance relative to current stabilization techniques. Subjective tests show that (1) both our stability and FPMI measurements can correctly compare the corresponding attributes of an FPV across different versions of the same content, and (2) our video processing system can effectively improve the viewing experience of FPVs.
topic First-Person Videos
viewing experience
video stabilization
url http://www.mdpi.com/2313-433X/4/9/106
work_keys_str_mv AT biaoma viewingexperiencemodeloffirstpersonvideos
AT amyrreibman viewingexperiencemodeloffirstpersonvideos
_version_ 1725975242714644480