An unified framework for shot boundary detection via active learning

Author

Chua, Tat-Seng ; Feng, HuaMin ; Chandrashekhara, A.

Author_Institution

Sch. of Comput., Nat. Univ. of Singapore, Singapore

Volume

2

fYear

2003

fDate

6-10 April 2003

Abstract

Video 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.

Keywords

edge detection; feature extraction; image motion analysis; image resolution; learning automata; noise; video signal processing; wavelet transforms; MPEG 7 video data set; SVM; abrupt transitions detection; active learning; feature vector; gradual transitions detection; motion-based feature vector; multiresolution edge phenomenon; noise tolerance characteristics; shot boundaries classification; support vector machine; temporal multiresolution analysis; video processing applications; video representation; video shot boundary detection; video shot transitions classification; wavelet; Colored noise; Extraterrestrial phenomena; Gunshot detection systems; Motion analysis; Signal resolution; Streaming media; Support vector machine classification; Support vector machines; Testing; Wavelet analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1202499

Filename

1202499