Fluctuation-Based Fade Detection for Local Scene Changes

In recent years, fade detection algorithms can classify fade scenes in massive video libraries have been developed. However, these algorithms misclassify some non-fade scenes as fade scenes, especially dissolve scenes and scenes with captions or flashing light sources. This paper proposes a new fade...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sangho Yoon, Chanhee Lee, Ho Sub Lee, Young Hwan Kim, Seokhyeong Kang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Algorithm design and analysis change detection algorithms machine learning algorithms video signal processing Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/853c47fcbf8e49858747df1b96c6e937
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:853c47fcbf8e49858747df1b96c6e937
record_format	dspace
spelling	oai:doaj.org-article:853c47fcbf8e49858747df1b96c6e9372021-11-18T00:01:37ZFluctuation-Based Fade Detection for Local Scene Changes2169-353610.1109/ACCESS.2021.3125731https://doaj.org/article/853c47fcbf8e49858747df1b96c6e9372021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9605601/https://doaj.org/toc/2169-3536In recent years, fade detection algorithms can classify fade scenes in massive video libraries have been developed. However, these algorithms misclassify some non-fade scenes as fade scenes, especially dissolve scenes and scenes with captions or flashing light sources. This paper proposes a new fade detection algorithm that uses similarity tendencies of luminance transitions to overcome such obstacles. To prevent detection accuracy degradation by letterboxing and captions, video frames are simplified. Then, fade candidates are detected by transition boundary detection using the angular and curvature characteristics of the luminance vectors. Finally, luminance flipping detection improves the detection accuracy by extracting the luminance retrograde phenomenon that occurs with flashing or light source movements. Through objective evaluation using <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score, the detection accuracy of the proposed algorithm was 0.884, which is an increase of 0.187 (21.2% improvement) compared with the average <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score of existing high-performance methods.Sangho YoonChanhee LeeHo Sub LeeYoung Hwan KimSeokhyeong KangIEEEarticleAlgorithm design and analysischange detection algorithmsmachine learning algorithmsvideo signal processingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149732-149743 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Algorithm design and analysis change detection algorithms machine learning algorithms video signal processing Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Algorithm design and analysis change detection algorithms machine learning algorithms video signal processing Electrical engineering. Electronics. Nuclear engineering TK1-9971 Sangho Yoon Chanhee Lee Ho Sub Lee Young Hwan Kim Seokhyeong Kang Fluctuation-Based Fade Detection for Local Scene Changes
description	In recent years, fade detection algorithms can classify fade scenes in massive video libraries have been developed. However, these algorithms misclassify some non-fade scenes as fade scenes, especially dissolve scenes and scenes with captions or flashing light sources. This paper proposes a new fade detection algorithm that uses similarity tendencies of luminance transitions to overcome such obstacles. To prevent detection accuracy degradation by letterboxing and captions, video frames are simplified. Then, fade candidates are detected by transition boundary detection using the angular and curvature characteristics of the luminance vectors. Finally, luminance flipping detection improves the detection accuracy by extracting the luminance retrograde phenomenon that occurs with flashing or light source movements. Through objective evaluation using <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score, the detection accuracy of the proposed algorithm was 0.884, which is an increase of 0.187 (21.2% improvement) compared with the average <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> score of existing high-performance methods.
format	article
author	Sangho Yoon Chanhee Lee Ho Sub Lee Young Hwan Kim Seokhyeong Kang
author_facet	Sangho Yoon Chanhee Lee Ho Sub Lee Young Hwan Kim Seokhyeong Kang
author_sort	Sangho Yoon
title	Fluctuation-Based Fade Detection for Local Scene Changes
title_short	Fluctuation-Based Fade Detection for Local Scene Changes
title_full	Fluctuation-Based Fade Detection for Local Scene Changes
title_fullStr	Fluctuation-Based Fade Detection for Local Scene Changes
title_full_unstemmed	Fluctuation-Based Fade Detection for Local Scene Changes
title_sort	fluctuation-based fade detection for local scene changes
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/853c47fcbf8e49858747df1b96c6e937
work_keys_str_mv	AT sanghoyoon fluctuationbasedfadedetectionforlocalscenechanges AT chanheelee fluctuationbasedfadedetectionforlocalscenechanges AT hosublee fluctuationbasedfadedetectionforlocalscenechanges AT younghwankim fluctuationbasedfadedetectionforlocalscenechanges AT seokhyeongkang fluctuationbasedfadedetectionforlocalscenechanges
_version_	1718425235129106432

Fluctuation-Based Fade Detection for Local Scene Changes

Ejemplares similares