Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/39989
DC FieldValue
dc.titleAn unified framework for shot boundary detection via active learning
dc.contributor.authorChua, T.-S.
dc.contributor.authorFeng, H.
dc.contributor.authorChandrashekhara, A.
dc.date.accessioned2013-07-04T07:54:09Z
dc.date.available2013-07-04T07:54:09Z
dc.date.issued2003
dc.identifier.citationChua, T.-S.,Feng, H.,Chandrashekhara, A. (2003). An unified framework for shot boundary detection via active learning. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2 : 845-848. ScholarBank@NUS Repository.
dc.identifier.issn15206149
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39989
dc.description.abstractVideo shot boundary detection is an important step in many video processing applications. We observe that video shot boundary is a multi-resolution edge phenomenon in the feature space. In this paper, we expanded our previous temporal multi-resolution analysis (TMRA) work by introducing the new feature vector based on motion. Further we employ the support vector machine (SVM) to refine the classification of shot boundaries. The resulting framework has been tested on the MPEG 7 video data set, and has been shown to have good accuracy for both the detection of abrupt and gradual transitions as well as their boundaries. It also has good noise tolerance characteristics.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.sourcetitleICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
dc.description.volume2
dc.description.page845-848
dc.description.codenIPROD
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

103
checked on Jan 20, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.