Extracting photographic images from video
First Claim
Patent Images
1. A method of generating photographs from a video, the method comprising:
- identifying segments of the video for which frame-to-frame background motion is less than a threshold; and
for each of the segments, combining video frames in the segment to generate a photograph representative of the segment.
5 Assignments
0 Petitions
Accused Products
Abstract
Generating photographs from a video. Segments of the video for which frame-to-frame background motion is less than a threshold are identified. For each of the segments, video frames in the segment are combined to generate a photograph representative of the segment.
221 Citations
12 Claims
-
1. A method of generating photographs from a video, the method comprising:
-
identifying segments of the video for which frame-to-frame background motion is less than a threshold; and
for each of the segments, combining video frames in the segment to generate a photograph representative of the segment. - View Dependent Claims (2, 3, 4, 5, 6, 7)
automatically detecting a scene cut in the video; and
selecting at least one video frame of a segment of the video that follows the scene cut to be a photograph.
-
-
3. The method of claim 1 wherein combining the video frames to generate a photograph comprises stitching images in the video frames together to generate a panoramic photograph.
-
4. The method of claim 1 wherein combining video frames to generate a photograph comprises blending pixels from the video frames to generate a photograph having higher resolution than any one of the video frames.
-
5. The method of claim 1 wherein combining video frames to generate a photograph comprises blending pixels from the video frames to form a multi-resolution photograph.
-
6. The method of claim 1 wherein identifying segments of the video for which frameto-frame background motion is less than a threshold comprises identifying a succession of frames of the video that each include a portion of an image in a preceding frame.
-
7. The method of claim 6 wherein identifying the succession of frames of the video that each include a portion of an image in a preceding frame comprises removing a dynamic object from at least one frame of the succession of frames before comparing the at least one frame to a preceding frame in the succession of frames.
-
8. An apparatus for generating photographs from a video, the apparatus comprising:
-
a scene change estimator to identify segments of the video for which frame-to-frame background motion is less than a threshold; and
a still image constructor to combine video frames in the segment to generate a photograph representative of the segment.
-
-
9. An apparatus for generating photographs from a video, the apparatus comprising:
-
means for identifying segments of the video for which frame-to-frame background motion is less than a threshold; and
means for combining video frames in the segment to generate a photograph representative of the segment.
-
-
10. An article of manufacture including one or more computer-readable media that embody a program of instructions for generating photographs from a video, wherein the program of instructions, when executed by a processing unit, causes the processing unit to:
-
identify segments of the video for which frame-to-frame background motion is less than a threshold; and
for each of the segments, combine video frames in the segment to generate a photograph representative of the segment. - View Dependent Claims (11, 12)
-
Specification