DocumentCode :
2670744
Title :
Model based video segmentation
Author :
Li, Dalong ; Lu, Hanqing
Author_Institution :
Inst. of Autom., Acad. Sinica, China
fYear :
2000
fDate :
2000
Firstpage :
120
Lastpage :
129
Abstract :
With the fast growth of video resources, efficient video classification and management are becoming more and more important. Video partitioning is a key issue in video classification. The video partitioning involves the detection of boundaries between uninterrupted segments (video shots) of scenes. Shot boundaries can be classified into two categories, gradual transition and instantaneous change (called camera break). Detection of a gradual transition is considered to be difficult. Block-based image comparison was proposed to detect shot boundaries. Unfortunately, if the differences of the corresponding blocks in the images are measured by gray levels, the method will make false alarms when the gray level change suddenly due to reasons other than shot shifts such as illumination variation which is common in news video. What is more, the step-variable algorithm can not distinguish wipe and dissolve. It is likely that step-variable algorithm will make false alarms of gradual transitions. In this paper, the proposed algorithm named MVS (model based video segmentation) can distinguish illumination variation from camera breaks as well as wipe from dissolve. Moreover, the positions of the gradual transition are located correctly. MVS is especially efficient in detecting wipes. Experimental results are reported in the paper to validate the proposed method
Keywords :
image classification; image segmentation; image sequences; video signal processing; MVS; Video partitioning; block-based image comparison; boundaries DETECTION; camera break; dissolve detection; efficient video classification; efficient video management; experimental results; gradual transition; gray levels; illumination variation; instantaneous change; model based video segmentation; news video; step-variable algorithm; video shots; wipe detection; Automation; Cameras; Change detection algorithms; Gunshot detection systems; Histograms; Image segmentation; Layout; Lighting; Partitioning algorithms; Resource management;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Systems, 2000. SiPS 2000. 2000 IEEE Workshop on
Conference_Location :
Lafayette, LA
ISSN :
1520-6130
Print_ISBN :
0-7803-6488-0
Type :
conf
DOI :
10.1109/SIPS.2000.886710
Filename :
886710
Link To Document :
بازگشت