Feature extraction and statistical analysis of videos for cinemetric applications

Christos Avgerinos; Nikos Nikolaidis; Vasileios Mygdalis; Ioannis Pitas

doi:10.1109/DMIAF.2016.7574926

Feature extraction and statistical analysis of videos for cinemetric applications

Christos Avgerinos, Nikos Nikolaidis, Vasileios Mygdalis, Ioannis Pitas

Department of Electrical & Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

3 Citations (Scopus)

251 Downloads (Pure)

Abstract

In this paper, we describe a framework for the extraction of low-level and high level information from movies in order to be used for cinemetric applications. The developed framework analyses the available video content and extracts characteristics related to color, motion, contrast, shot length, tempo, face to frame ratios etc. The extracted information is stored in MPEG 7 AVDP profile format, which is a standard description format that can be imported to related cinemetric
applications. We applied the developed framework in a collection of downloaded videos, as well as 3 stereoscopic movies.

Original language	English
Title of host publication	2016 Digital Media Industry & Academic Forum (DMIAF 2016
Subtitle of host publication	Proceedings of a meeting held 4-6 July 2016, Santorini, Greece
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	172-175
Number of pages	4
ISBN (Electronic)	9781509010004
ISBN (Print)	9781509010011
DOIs	https://doi.org/10.1109/DMIAF.2016.7574926
Publication status	Published - Oct 2016
Event	IEEE Digital Media Industry and Academic Forum - Santorini, Greece Duration: 4 Jul 2016 → 6 Jul 2016

Conference

Conference	IEEE Digital Media Industry and Academic Forum
Abbreviated title	DMIAF
Country	Greece
City	Santorini
Period	4/07/16 → 6/07/16

Keywords

Motion pictures
Image color analysis
Videos
Face
Data mining
Rhythm
Feature extraction

Access to Document

10.1109/DMIAF.2016.7574926

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at http://dx.doi.org/10.1109/DMIAF.2016.7574926. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 591 KB

Fingerprint Dive into the research topics of 'Feature extraction and statistical analysis of videos for cinemetric applications'. Together they form a unique fingerprint.

Cite this

Avgerinos, C., Nikolaidis, N., Mygdalis, V., & Pitas, I. (2016). Feature extraction and statistical analysis of videos for cinemetric applications. In 2016 Digital Media Industry & Academic Forum (DMIAF 2016 : Proceedings of a meeting held 4-6 July 2016, Santorini, Greece (pp. 172-175). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/DMIAF.2016.7574926

@inproceedings{ac455fa2f5a84c978a9236d36f4fe6bc,

title = "Feature extraction and statistical analysis of videos for cinemetric applications",

abstract = "In this paper, we describe a framework for the extraction of low-level and high level information from movies in order to be used for cinemetric applications. The developed framework analyses the available video content and extracts characteristics related to color, motion, contrast, shot length, tempo, face to frame ratios etc. The extracted information is stored in MPEG 7 AVDP profile format, which is a standard description format that can be imported to related cinemetricapplications. We applied the developed framework in a collection of downloaded videos, as well as 3 stereoscopic movies.",

keywords = "Motion pictures, Image color analysis, Videos, Face, Data mining, Rhythm, Feature extraction",

author = "Christos Avgerinos and Nikos Nikolaidis and Vasileios Mygdalis and Ioannis Pitas",

year = "2016",

month = oct,

doi = "10.1109/DMIAF.2016.7574926",

language = "English",

isbn = "9781509010011",

pages = "172--175",

booktitle = "2016 Digital Media Industry & Academic Forum (DMIAF 2016",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "IEEE Digital Media Industry and Academic Forum, DMIAF ; Conference date: 04-07-2016 Through 06-07-2016",

}

Avgerinos, C, Nikolaidis, N, Mygdalis, V & Pitas, I 2016, Feature extraction and statistical analysis of videos for cinemetric applications. in 2016 Digital Media Industry & Academic Forum (DMIAF 2016 : Proceedings of a meeting held 4-6 July 2016, Santorini, Greece. Institute of Electrical and Electronics Engineers (IEEE), pp. 172-175, IEEE Digital Media Industry and Academic Forum, Santorini, Greece, 4/07/16. https://doi.org/10.1109/DMIAF.2016.7574926

Feature extraction and statistical analysis of videos for cinemetric applications. / Avgerinos, Christos; Nikolaidis, Nikos; Mygdalis, Vasileios; Pitas, Ioannis.

2016 Digital Media Industry & Academic Forum (DMIAF 2016 : Proceedings of a meeting held 4-6 July 2016, Santorini, Greece. Institute of Electrical and Electronics Engineers (IEEE), 2016. p. 172-175.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Feature extraction and statistical analysis of videos for cinemetric applications

AU - Avgerinos, Christos

AU - Nikolaidis, Nikos

AU - Mygdalis, Vasileios

AU - Pitas, Ioannis

PY - 2016/10

Y1 - 2016/10

N2 - In this paper, we describe a framework for the extraction of low-level and high level information from movies in order to be used for cinemetric applications. The developed framework analyses the available video content and extracts characteristics related to color, motion, contrast, shot length, tempo, face to frame ratios etc. The extracted information is stored in MPEG 7 AVDP profile format, which is a standard description format that can be imported to related cinemetricapplications. We applied the developed framework in a collection of downloaded videos, as well as 3 stereoscopic movies.

AB - In this paper, we describe a framework for the extraction of low-level and high level information from movies in order to be used for cinemetric applications. The developed framework analyses the available video content and extracts characteristics related to color, motion, contrast, shot length, tempo, face to frame ratios etc. The extracted information is stored in MPEG 7 AVDP profile format, which is a standard description format that can be imported to related cinemetricapplications. We applied the developed framework in a collection of downloaded videos, as well as 3 stereoscopic movies.

KW - Motion pictures

KW - Image color analysis

KW - Videos

KW - Face

KW - Data mining

KW - Rhythm

KW - Feature extraction

U2 - 10.1109/DMIAF.2016.7574926

DO - 10.1109/DMIAF.2016.7574926

M3 - Conference Contribution (Conference Proceeding)

SN - 9781509010011

SP - 172

EP - 175

BT - 2016 Digital Media Industry & Academic Forum (DMIAF 2016

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - IEEE Digital Media Industry and Academic Forum

Y2 - 4 July 2016 through 6 July 2016

ER -

Avgerinos C, Nikolaidis N, Mygdalis V, Pitas I. Feature extraction and statistical analysis of videos for cinemetric applications. In 2016 Digital Media Industry & Academic Forum (DMIAF 2016 : Proceedings of a meeting held 4-6 July 2016, Santorini, Greece. Institute of Electrical and Electronics Engineers (IEEE). 2016. p. 172-175 https://doi.org/10.1109/DMIAF.2016.7574926