Key-frame extraction from video

Claim 3

The method of claim 1 , wherein selecting includes selecting the key-frames in response to a video content change in the corresponding video frames.

Claim 4

The method of claim 2 , wherein selecting includes determining the video content change by determining a histogram difference in the corresponding video frames.

Claim 5

The method of claim 1 , wherein selecting includes selecting the key-frames in response to an entropy for each corresponding video frame.

Claim 6

The method of claim 1 , wherein selecting includes selecting the key-frames in response to a sharpness for each corresponding video frame.

Claim 7

The method of claim 1 , wherein selecting includes selecting the key-frames in response to a contrast for each corresponding video frame.

Claim 8

The method of claim 1 , wherein selecting includes selecting the key-frames in response to a user selected mode.

Claim 9

The method of claim 7 , wherein selecting a set of key-frames includes selecting a fixed number of key-frames for the video as specified by the user selected mode.

Claim 10

The method of claim 7 , wherein selecting includes selecting a fixed rate of key-frames for the video as specified by the user selected mode.

Claim 11

The method of claim 7 , wherein selecting includes selecting one key-frame for each shot in the video as specified by the user selected mode.

Claim 12

A video system including a key-frame extractor that segments a video of video frames into a set of shots each having a set of the video of the video frames and that selects a set of key-frames from the shots in response to an image quality of the corresponding video frames, wherein the key-frame extractor segments the video by: determining a color histogram for each video frame; determining a difference in the color histograms of each pair of a plurality of pairs of consecutive video frames of the video of video frames; determining a mean and variance in the difference in the color histograms of each pair; determining an adaptive threshold based on the mean and the variance; and, detecting shot boundaries within the video using the adaptive threshold.

Claim 13

A video system including a key-frame extractor that segments a video of video frames into a set of shots each having a set of the video of the video frames and that selects a set of key-frames from the shots in response to an image quality of the corresponding video frames, wherein the key-frame extractor segments the video by: determining a color histogram for each video frame; determining a difference in the color histograms of each pair of a plurality of pairs of consecutive video frames of the video of video frames; determining a mean and variance in the difference in the color histograms of each pair; determining an adaptive threshold based on the mean and the variance; and, detecting shot boundaries within the video using the adaptive threshold.

Claim 14

The video system of claim 11 , wherein the key-frame extractor selects the key-frames in response to a video content change in the corresponding video frames.

Claim 15

The video system of claim 12 , wherein the key-frame extractor selects the key-frames in response to a user selected mode.

Claim 16

The video system of claim 13 , wherein the user selected mode specifies a fixed number of key-frames for the video.

Claim 17

The video system of claim 14 , wherein the key-frame extractor selects the key-frames by ranking the shots according length and content.

Claim 18

The video system of claim 15 , wherein the key-frame extractor selects the key-frames by splitting one of the shots into two shots at a video frame having a greatest content change.

Claim 19

The video system of claim 14 , wherein the key-frame extractor selects the key-frames by removing a key-frame having a low image quality.

Claim 20

The video system of claim 14 , wherein the key-frame extractor selects the key-frames by removing a key-frame that corresponds to a short shot.

Claim 21

The video system of claim 13 , wherein the user selected mode specifies a fixed rate of key-frames for the video.

Claim 22

The video system of claim 19 , wherein the key-frame extractor selects the key-frames by dividing the video into a set of segments having a fixed length in response to the fixed rate by allocating one key-frame to each of a set of segments in the video in response to a set of shot boundaries and content changes.