Shot boundary detection based on orthogonal polynomial

Shot boundary detection (SBD) is a substantial step in video content analysis, indexing, retrieval, and summarization. SBD is the process of automatically partitioning video into its basic units, known as shots, through detecting transitions between shots. The design of SBD algorithms developed from...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multimedia tools and applications Jg. 78; H. 14; S. 20361 - 20382
Hauptverfasser: Abdulhussain, Sadiq H., Ramli, Abd Rahman, Mahmmod, Basheera M., Saripan, M. Iqbal, Al-Haddad, S. A. R., Jassim, Wissam A.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.07.2019
Springer Nature B.V
Schlagworte:
Algorithms
Computer Communication Networks
Computer Science
Computer vision
Content analysis
Data Structures and Information Theory
Multimedia Information Systems
Polynomials
Redundancy
Signal processing
Special Purpose and Application-Based Systems
Support vector machines
Video data
Abrupt transition
Hard transition
Temporal video segmentation
Shot boundary detection
Orthogonal polynomial
Orthogonal moments
ISSN:1380-7501, 1573-7721
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Shot boundary detection (SBD) is a substantial step in video content analysis, indexing, retrieval, and summarization. SBD is the process of automatically partitioning video into its basic units, known as shots, through detecting transitions between shots. The design of SBD algorithms developed from simple feature comparison to rigorous probabilistic and using of complex models. Nevertheless, accelerate the detection of transitions with higher accuracy need to be improved. Extensive research has employed orthogonal polynomial (OP) and their moments in computer vision and signal processing owing to their powerful performance in analyzing signals. A new SBD algorithm based on OP has been proposed in this paper. The Features are derived from orthogonal transform domain (moments) to detect the hard transitions in video sequences. Moments are used because of their ability to represent signal (video frame) without information redundancy. These features are the moments of smoothed and gradients of video frames. The moments are computed using a developed OP which is squared Krawtchouk-Tchebichef polynomial. These moments (smoothed and gradients) are fused to form a feature vector. Finally, the support vector machine is utilized to detect hard transitions. In addition, a comparison between the proposed algorithm and other state-of-the-art algorithms is performed to reinforce the capability of the proposed work. The proposed algorithm is examined using three well-known datasets which are TRECVID2005, TRECVID2006, and TRECVID2007. The outcomes of the comparative analysis show the superior performance of the proposed algorithm against other existing algorithms.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-019-7364-3