Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections
Joint Authors
Xiao, Yongliang
Xia, Limin
Zhu, Shaoping
Huang, Dazu
Xie, Jianquan
Source
Mathematical Problems in Engineering
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-11-27
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
A novel video shot boundary recognition method is proposed, which includes two stages of video feature extraction and shot boundary recognition.
Firstly, we use adaptive locality preserving projections (ALPP) to extract video feature.
Unlike locality preserving projections, we define the discriminating similarity with mode prior probabilities and adaptive neighborhood selection strategy which make ALPP more suitable to preserve the local structure and label information of the original data.
Secondly, we use an optimized multiple kernel support vector machine to classify video frames into boundary and nonboundary frames, in which the weights of different types of kernels are optimized with an ant colony optimization method.
Experimental results show the effectiveness of our method.
American Psychological Association (APA)
Xiao, Yongliang& Xia, Limin& Zhu, Shaoping& Huang, Dazu& Xie, Jianquan. 2013. Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections. Mathematical Problems in Engineering،Vol. 2013, no. 2013, pp.1-9.
https://search.emarefa.net/detail/BIM-1009102
Modern Language Association (MLA)
Xiao, Yongliang…[et al.]. Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections. Mathematical Problems in Engineering No. 2013 (2013), pp.1-9.
https://search.emarefa.net/detail/BIM-1009102
American Medical Association (AMA)
Xiao, Yongliang& Xia, Limin& Zhu, Shaoping& Huang, Dazu& Xie, Jianquan. Video Shot Boundary Recognition Based on Adaptive Locality Preserving Projections. Mathematical Problems in Engineering. 2013. Vol. 2013, no. 2013, pp.1-9.
https://search.emarefa.net/detail/BIM-1009102
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1009102