Title :
A method for shot boundary detection with automatic threshold
Author :
Yong, Cheng ; Xu, Yang ; De, Xu
Author_Institution :
Dept. of Comput. Sci. & Technol., Northern Jiaotong Univ, Beijing, China
Abstract :
An important step in content-based video retrieval is the temporal segmentation of video. In this paper we give an overview of some existing shot boundary detection algorithms. that operate on uncompressed video stream. After that, we propose an algorithm for shot boundary detection that integrates the spatial and color features of frames. Our method is not sensitive to brightness change and quick motion. Therefore, it can improve the precision of detecting shot boundaries. Finally we give the experimental results and draw our conclusion.
Keywords :
content-based retrieval; edge detection; feature extraction; image colour analysis; image retrieval; image segmentation; video databases; automatic threshold; color features; content-based video retrieval; precision; shot boundary detection; spatial features; temporal video segmentation; uncompressed video stream; video databases; Cameras; Change detection algorithms; Colored noise; Computer aided instruction; Database systems; Gunshot detection systems; Object detection; Pixel; Software libraries; Videos;
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
DOI :
10.1109/TENCON.2002.1181342
