SVM-based shot boundary detection with a novel feature

被引：11

作者：

Matsumoto, Kazunorri ^{[1
]}

Naito, Masaki ^{[1
]}

Hoashi, Keiichiro ^{[1
]}

Sugaya, Fumiaki ^{[1
]}

机构：

[1] KDDI R&D Labs Inc, 2-1-15 Ohara, Fujimino, Saitama 3568502, Japan

来源：

2006 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO - ICME 2006, VOLS 1-5, PROCEEDINGS | 2006年

关键词：

D O I：

10.1109/ICME.2006.262911

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes our new algorithm for shot boundary detection and its evaluation. We adopt a 2-stage data fusion approach with SVM technique to decide whether a boundary exists or not within a given video sequence. This approach is useful to avoid huge feature space problems, even when we adopt many promising features extracted from a video sequence. We also introduce a novel feature to improve detection. The feature consists of two kinds of values extracted from a local frame sequence. One is the image difference between the target frame and that synthesized from the neighbors. The other is the difference between neighbors. This feature can be extracted quickly with a least-square technique. Evaluation of our algorithm is conducted with the TPECVID evaluation framework. Our system obtained a high performance at a shot boundary detection task in TRECVID2005.

引用

页码：1837 / 1840

页数：4