Automatic live sport video streams curation system from user generated media

Kazuki Fujisawa, Yuko Hirabe, Hirohiko Suwa, Yutaka Arakawa, Keiichi Yasumoto

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Emerging Internet of Things (IoT) technologies will allow spectators in a sport game to produce various video streams from various angles. With existing technologies, however, it is difficult to process massive and various data streams for multi-channel contents in real-time. To solve this problem, we aim to construct a software agent (called "Curator") that compiles video contents automatically according to his/ her values. In this paper, we propose a system to automatically switch multiple video streams that general sports spectators have taken using Random Forests classifier. Meta data such as image feature data and game progress data is extracted for each video scene as the input of the classifier. For evaluation, we constructed a camera switching timing estimation model using the live TV broadcast of some baseball game data. A video of another baseball game was curated with the constructed model. As a result, our system predicted the camera switching timing with accuracy (F-measure) of 85.3% on weighted average for the base camera work and 99.7% for the fixed camera work.

Original languageEnglish
Title of host publicationSports Media, Marketing, and Management
Subtitle of host publicationBreakthroughs in Research and Practice
PublisherIGI Global
Pages417-435
Number of pages19
ISBN (Electronic)9781522554769
ISBN (Print)1522554750, 9781522554752
DOIs
Publication statusPublished - Mar 2 2018
Externally publishedYes

Fingerprint

Spectator
Baseball
Classifier
Software agents
Internet of things
Metadata
Evaluation
Data streams

All Science Journal Classification (ASJC) codes

  • Economics, Econometrics and Finance(all)
  • Business, Management and Accounting(all)

Cite this

Fujisawa, K., Hirabe, Y., Suwa, H., Arakawa, Y., & Yasumoto, K. (2018). Automatic live sport video streams curation system from user generated media. In Sports Media, Marketing, and Management: Breakthroughs in Research and Practice (pp. 417-435). IGI Global. https://doi.org/10.4018/978-1-5225-5475-2.ch022

Automatic live sport video streams curation system from user generated media. / Fujisawa, Kazuki; Hirabe, Yuko; Suwa, Hirohiko; Arakawa, Yutaka; Yasumoto, Keiichi.

Sports Media, Marketing, and Management: Breakthroughs in Research and Practice. IGI Global, 2018. p. 417-435.

Research output: Chapter in Book/Report/Conference proceedingChapter

Fujisawa, K, Hirabe, Y, Suwa, H, Arakawa, Y & Yasumoto, K 2018, Automatic live sport video streams curation system from user generated media. in Sports Media, Marketing, and Management: Breakthroughs in Research and Practice. IGI Global, pp. 417-435. https://doi.org/10.4018/978-1-5225-5475-2.ch022
Fujisawa K, Hirabe Y, Suwa H, Arakawa Y, Yasumoto K. Automatic live sport video streams curation system from user generated media. In Sports Media, Marketing, and Management: Breakthroughs in Research and Practice. IGI Global. 2018. p. 417-435 https://doi.org/10.4018/978-1-5225-5475-2.ch022
Fujisawa, Kazuki ; Hirabe, Yuko ; Suwa, Hirohiko ; Arakawa, Yutaka ; Yasumoto, Keiichi. / Automatic live sport video streams curation system from user generated media. Sports Media, Marketing, and Management: Breakthroughs in Research and Practice. IGI Global, 2018. pp. 417-435
@inbook{90950e1afb194c61895f553ef495ad2b,
title = "Automatic live sport video streams curation system from user generated media",
abstract = "Emerging Internet of Things (IoT) technologies will allow spectators in a sport game to produce various video streams from various angles. With existing technologies, however, it is difficult to process massive and various data streams for multi-channel contents in real-time. To solve this problem, we aim to construct a software agent (called {"}Curator{"}) that compiles video contents automatically according to his/ her values. In this paper, we propose a system to automatically switch multiple video streams that general sports spectators have taken using Random Forests classifier. Meta data such as image feature data and game progress data is extracted for each video scene as the input of the classifier. For evaluation, we constructed a camera switching timing estimation model using the live TV broadcast of some baseball game data. A video of another baseball game was curated with the constructed model. As a result, our system predicted the camera switching timing with accuracy (F-measure) of 85.3{\%} on weighted average for the base camera work and 99.7{\%} for the fixed camera work.",
author = "Kazuki Fujisawa and Yuko Hirabe and Hirohiko Suwa and Yutaka Arakawa and Keiichi Yasumoto",
year = "2018",
month = "3",
day = "2",
doi = "10.4018/978-1-5225-5475-2.ch022",
language = "English",
isbn = "1522554750",
pages = "417--435",
booktitle = "Sports Media, Marketing, and Management",
publisher = "IGI Global",

}

TY - CHAP

T1 - Automatic live sport video streams curation system from user generated media

AU - Fujisawa, Kazuki

AU - Hirabe, Yuko

AU - Suwa, Hirohiko

AU - Arakawa, Yutaka

AU - Yasumoto, Keiichi

PY - 2018/3/2

Y1 - 2018/3/2

N2 - Emerging Internet of Things (IoT) technologies will allow spectators in a sport game to produce various video streams from various angles. With existing technologies, however, it is difficult to process massive and various data streams for multi-channel contents in real-time. To solve this problem, we aim to construct a software agent (called "Curator") that compiles video contents automatically according to his/ her values. In this paper, we propose a system to automatically switch multiple video streams that general sports spectators have taken using Random Forests classifier. Meta data such as image feature data and game progress data is extracted for each video scene as the input of the classifier. For evaluation, we constructed a camera switching timing estimation model using the live TV broadcast of some baseball game data. A video of another baseball game was curated with the constructed model. As a result, our system predicted the camera switching timing with accuracy (F-measure) of 85.3% on weighted average for the base camera work and 99.7% for the fixed camera work.

AB - Emerging Internet of Things (IoT) technologies will allow spectators in a sport game to produce various video streams from various angles. With existing technologies, however, it is difficult to process massive and various data streams for multi-channel contents in real-time. To solve this problem, we aim to construct a software agent (called "Curator") that compiles video contents automatically according to his/ her values. In this paper, we propose a system to automatically switch multiple video streams that general sports spectators have taken using Random Forests classifier. Meta data such as image feature data and game progress data is extracted for each video scene as the input of the classifier. For evaluation, we constructed a camera switching timing estimation model using the live TV broadcast of some baseball game data. A video of another baseball game was curated with the constructed model. As a result, our system predicted the camera switching timing with accuracy (F-measure) of 85.3% on weighted average for the base camera work and 99.7% for the fixed camera work.

UR - http://www.scopus.com/inward/record.url?scp=85046581066&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046581066&partnerID=8YFLogxK

U2 - 10.4018/978-1-5225-5475-2.ch022

DO - 10.4018/978-1-5225-5475-2.ch022

M3 - Chapter

AN - SCOPUS:85046581066

SN - 1522554750

SN - 9781522554752

SP - 417

EP - 435

BT - Sports Media, Marketing, and Management

PB - IGI Global

ER -