Title :
A robust scene-change detection method for video segmentation
Author :
Huang, Chung-Lin ; Liao, Bing-Yao
Author_Institution :
Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fDate :
12/1/2001 12:00:00 AM
Abstract :
This paper proposes a new method that combines the intensity and motion information to detect scene changes such as abrupt scene changes and gradual scene changes. Two major features are chosen as the basic dissimilarity measures, and self- and cross-validation mechanisms are employed via a static scene test. We also develop a novel intensity statistics model for detecting gradual scene changes. Experimental results show that the proposed algorithms are effective and outperform the previous approaches
Keywords :
image motion analysis; image segmentation; image sequences; statistical analysis; video signal processing; abrupt scene changes; cross-validation mechanism; detection rate; dissimilarity measures; false alarm rate; gradual scene changes; intensity information; intensity statistics model; motion information; robust scene-change detection method; scene-change detection algorithm; self-validation mechanism; static scene test; threshold selection problem; video segmentation; video sequence; Automatic testing; Cameras; Image segmentation; Layout; Motion detection; Object detection; Robustness; Statistics; Video compression; Video sequences;
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on