完整後設資料紀錄
DC 欄位語言
dc.contributor.authorChen, Liang-Huaen_US
dc.contributor.authorLai, Yu-Chunen_US
dc.contributor.authorLiao, Hong-Yuanen_US
dc.date.accessioned2017-04-21T06:48:31Z-
dc.date.available2017-04-21T06:48:31Z-
dc.date.issued2006en_US
dc.identifier.isbn0-7695-2521-0en_US
dc.identifier.issn1051-4651en_US
dc.identifier.urihttp://hdl.handle.net/11536/135183-
dc.description.abstractScene extraction is the first step toward semantic understanding of the video. This paper presents an effective approach to video scene extraction based on the analysis of background images. Our approach exploits the fact that shots belonging to one particular scene often have similar background. Although part of the video frame is covered by foreground objects, background scene still can be reconstructed by mosaic technique. The proposed scene extraction algorithm consists of two main components: the determination of shot similarity measure and shot grouping process. In our approach, several low-level visual features are integrated to compute the similarity measure between two shots. On the other hand, high-level knowledge in cinematography is used to guide the shot grouping process. Experimental results show that our approach is promising and outperforms some existing technique.en_US
dc.language.isoen_USen_US
dc.titleVideo scene extraction using mosaic techniqueen_US
dc.typeProceedings Paperen_US
dc.identifier.journal18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, PROCEEDINGSen_US
dc.citation.spage723en_US
dc.citation.epage+en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000240707600176en_US
dc.citation.woscount2en_US
顯示於類別:會議論文