Hierarchical video summarization for medical data

Get BibTex-formatted data

Download

PDF

Author

X Zhu, J Fan, AK Elmagarmid, WG Aref

Entry type

inproceedings

Abstract

To provide users with an overview of medical video content at various levels of abstraction which can be used for more efficient database browsing and access, a hierarchical video summarization strategy has been developed and is presented in this paper. To generate an overview, the key frames of a video are preprocessed to extract special frames (black frames, slides, clip art, sketch drawings) and special regions (faces, skin or blood-red areas). A shot grouping method is then applied to merge the spatially or temporally related shots into groups. The visual features and knowledge from the video shots are integrated to assign the groups into predefined semantic categories. Based on the video groups and their semantic categories, video summaries for different levels are constructed by group merging, hierarchical group clustering and semantic category selection. Based on this strategy, a user can select the layer of the summary to access. The higher the layer, the more concise the video summary; the lower the layer, the greater the detail contained in the summary.

Download

PDF

Date

2001 – 12

Booktitle

Proceedings of SPIE

Journal

Storage and Retrieval for Media Databases 2002

Key alpha

Aref

Pages

395-406

Volume

4676

Publication Date

2001-12-01

BibTex-formatted data

To refer to this entry, you may select and copy the text below and paste it into your BibTex document. Note that the text may not contain all macros that BibTex supports.

@Inproceedings{ Aref,
	title = "Hierarchical video summarization for medical data",
	author = "X Zhu, J Fan, AK Elmagarmid, WG Aref",
	year = "2001",
	month = "12",
	booktitle = "Proceedings of SPIE",
	journal = "Storage and Retrieval for Media Databases 2002",
	pages = "395-406",
	volume = "4676",
	abstract = "To provide users with an overview of medical video content at various levels of abstraction which can be used for more efficient database browsing and access, a hierarchical video summarization strategy has been developed and is presented in this paper. To generate an overview, the key frames of a video are preprocessed to extract special frames (black frames, slides, clip art, sketch drawings) and special regions (faces, skin or blood-red areas). A shot grouping method is then applied to merge the spatially or temporally related shots into groups. The visual features and knowledge from the video shots are integrated to assign the groups into predefined semantic categories. Based on the video groups and their semantic categories, video summaries for different levels are constructed by group merging, hierarchical group clustering and semantic category selection. Based on this strategy, a user can select the layer of the summary to access. The higher the layer, the more concise the video summary; the lower the layer, the greater the detail contained in the summary. ",
}