Scene-change detection method that distinguishes between gradual

Television – Special applications – Observation of or from a specific location

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

348700, H04N 718

Patent

active

058017658

ABSTRACT:
A video for one frame is captured and two adjacent frames are compared, the result of which is detected as a change degree of the video. Then, based on the magnitude of the change degree, it is determined whether a scene change (SC) exists. If an SC exists, it is examined whether its change degree alters rapidly or gradually, to determine the SC as a momentum or gradual SC. For the momentum SC, its determination point is detected as the momentum SC. For the gradual SC, its determination points is detected as the start of the gradual SC, thereafter, its end is detected. According, for one gradual SC, plural SC's are not detected and a midway illegible video is not indicated as an index picture.

REFERENCES:
patent: 4677466 (1987-06-01), Lert, Jr. et al.
patent: 5455561 (1995-10-01), Brown
patent: 5589884 (1996-12-01), Ohguchi
patent: 5654772 (1997-08-01), Mester et al.
"Automatic indexing method and object search method for color video picture", Johoshori Gakkai theses, vol. 33, No. 4, Apr., 1992.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Scene-change detection method that distinguishes between gradual does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Scene-change detection method that distinguishes between gradual, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Scene-change detection method that distinguishes between gradual will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-275122

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.