Hierarchical video summarization for medical data

Xingquan Zhu, Jianping Fan, Ahmed Elmagarmid, Walid G. Aref

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsM.M. Yeung, C.S. Li, R.W. Lienhart
Pages395-406
Number of pages12
Volume4676
DOIs
Publication statusPublished - 2002
Externally publishedYes
EventStorage and Retrieval for Media Databases 2002 - San Jose, CA, United States
Duration: 23 Jan 200225 Jan 2002

Other

OtherStorage and Retrieval for Media Databases 2002
CountryUnited States
CitySan Jose, CA
Period23/1/0225/1/02

Fingerprint

Semantics
semantics
shot
Merging
Skin
Blood
clips
arts
chutes
blood

Keywords

  • Hierarchical video summarization
  • Video classification
  • Video processing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Zhu, X., Fan, J., Elmagarmid, A., & Aref, W. G. (2002). Hierarchical video summarization for medical data. In M. M. Yeung, C. S. Li, & R. W. Lienhart (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4676, pp. 395-406) https://doi.org/10.1117/12.451110

Hierarchical video summarization for medical data. / Zhu, Xingquan; Fan, Jianping; Elmagarmid, Ahmed; Aref, Walid G.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / M.M. Yeung; C.S. Li; R.W. Lienhart. Vol. 4676 2002. p. 395-406.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhu, X, Fan, J, Elmagarmid, A & Aref, WG 2002, Hierarchical video summarization for medical data. in MM Yeung, CS Li & RW Lienhart (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4676, pp. 395-406, Storage and Retrieval for Media Databases 2002, San Jose, CA, United States, 23/1/02. https://doi.org/10.1117/12.451110
Zhu X, Fan J, Elmagarmid A, Aref WG. Hierarchical video summarization for medical data. In Yeung MM, Li CS, Lienhart RW, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 4676. 2002. p. 395-406 https://doi.org/10.1117/12.451110
Zhu, Xingquan ; Fan, Jianping ; Elmagarmid, Ahmed ; Aref, Walid G. / Hierarchical video summarization for medical data. Proceedings of SPIE - The International Society for Optical Engineering. editor / M.M. Yeung ; C.S. Li ; R.W. Lienhart. Vol. 4676 2002. pp. 395-406
@inproceedings{77111fb31c124469acfc57b6738d9df4,
title = "Hierarchical video summarization for medical data",
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.",
keywords = "Hierarchical video summarization, Video classification, Video processing",
author = "Xingquan Zhu and Jianping Fan and Ahmed Elmagarmid and Aref, {Walid G.}",
year = "2002",
doi = "10.1117/12.451110",
language = "English",
volume = "4676",
pages = "395--406",
editor = "M.M. Yeung and C.S. Li and R.W. Lienhart",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Hierarchical video summarization for medical data

AU - Zhu, Xingquan

AU - Fan, Jianping

AU - Elmagarmid, Ahmed

AU - Aref, Walid G.

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

KW - Hierarchical video summarization

KW - Video classification

KW - Video processing

UR - http://www.scopus.com/inward/record.url?scp=0036029676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036029676&partnerID=8YFLogxK

U2 - 10.1117/12.451110

DO - 10.1117/12.451110

M3 - Conference contribution

VL - 4676

SP - 395

EP - 406

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Yeung, M.M.

A2 - Li, C.S.

A2 - Lienhart, R.W.

ER -