A unified approach to content-based indexing and retrieval of digital videos from television archives.

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.creatorSouza, Celso L. de-
Autor(es): dc.creatorPádua, Flávio L. C.-
Autor(es): dc.creatorNunes, Cristiano F. G.-
Autor(es): dc.creatorAssis, Guilherme Tavares de-
Autor(es): dc.creatorSilva, Giani David-
Data de aceite: dc.date.accessioned2019-11-06T13:32:01Z-
Data de disponibilização: dc.date.available2019-11-06T13:32:01Z-
Data de envio: dc.date.issued2015-01-26-
Data de envio: dc.date.issued2015-01-26-
Data de envio: dc.date.issued2014-
Fonte completa do material: dc.identifierhttp://www.repositorio.ufop.br/handle/123456789/4370-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/capes/557421-
Descrição: dc.descriptionThis work addresses the development of a unified approach to content-based indexing and retrieval of digital videos from television archives. The proposed approach has been designed to deal with arbitrary television genres, making it suitable for various applications. To achieve this goal, the main steps of a content-based video retrieval system are addressed in this work, namely: video segmentation, key-frame extraction, content-based video indexing and the video retrieval operation itself. Video segmentation is addressed as a typical TV broadcast structuring problem, which consists in automatically determining the boundaries of each broadcasted program (like movies, news, among others) and inter-program (for instance, commercials). Specifically, to segment the videos, Electronic Program Guide (EPG) metadata is combined with the detection of two special cues, namely, audio cuts (silence) and dark monochrome frames. On the other hand, a color histogram-based approach performs key-frame extraction. Video indexing and retrieval are accomplished by using hashing and k-d tree methods, while visual signatures containing color, shape and texture information are estimated for the key-frames, by using image and frequency domain techniques. Experimental results with the dataset of a multimedia information system especially developed for managing television broadcast archives demonstrate that our approach works efficiently, retrieving videos in 0.16 seconds on average and achieving recall, precision and F1 measure values, as high as 0.76, 0.97 and 0.86 respectively.-
Idioma: dc.languageen-
Direitos: dc.rightsDisponível sob Licença Creative Commons do tipo Attribution 3.0 Unported, que permite copiar, distribuir, transmitir e adaptar o trabalho, desde que seja citado o autor e licenciante. Fonte: Artificial Intelligence Research <http://www.sciedu.ca/journal/index.php/air/index>. Acesso em: 16 jan. 2015.-
Palavras-chave: dc.subjectTelevision archives-
Palavras-chave: dc.subjectRetrieval vídeo-
Palavras-chave: dc.subjectTV broadcast structuring-
Palavras-chave: dc.subjectVideo indexing-
Título: dc.titleA unified approach to content-based indexing and retrieval of digital videos from television archives.-
Aparece nas coleções:Repositório Institucional - UFOP

Não existem arquivos associados a este item.