Efficient method for assembling key video snippets to form a video summary

• US 8,432,965 B2
• Filed: 05/25/2010
• Issued: 04/30/2013
• Est. Priority Date: 05/25/2010
• Status: Active Grant

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Intellectual Ventures Fund 83 LLC (Intellectual Ventures LLC)
• Inventors: Deever, Aaron T.
• Primary Examiner(s): Czekaj, David
• Assistant Examiner(s): Beck, Leron
• Application Number:
  US12/786,483
• Publication Number:
  US 20110293018A1
• Time in Patent Office: 1,071 Days
• Field of Search: 375/240.25
• US Class Current: 375/240.01
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G11B 2020/10537 Audio or video recording
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: G11B 27/322 used signal is digitally coded
• CPC Class Codes: H04N 5/772 the recording apparatus and the television camera being placed in the same enclosure
• CPC Class Codes: H04N 5/91 Television signal processing therefor
• CPC Class Codes: H04N 9/8042 involving data reduction
• CPC Class Codes: H04N 9/8063 using time division multiplex of the PCM audio and PCM video signals

Abstract

A method for forming a video summary for a digital video sequence. The method includes capturing a digital video sequence with a digital video capture device, wherein the digital video sequence includes a plurality of video frames. At least one of the video frames in the digital video sequence is analyzed at the time the digital video sequence is captured to determine one or more feature values. The digital video sequence; is compressed and stored in a processor-accessible memory. The feature values are analyzed, without decompressing the stored compressed digital video sequence, to identify one or more key video snippets, each key video snippet corresponding to a set of video frames from the digital video sequence. The key video snippets are assembled to form a video summary which is stored in a processor-accessible memory.

Claims

1. A method for forming a video summary for a digital video sequence captured with a digital video capture device, comprising:

capturing a digital video sequence with the digital video capture device, wherein the digital video sequence includes a plurality of video frames;

using a processor to automatically analyze at least one of the video frames in the digital video sequence at the time the digital video sequence is captured to determine one or more feature values;

compressing the digital video sequence, wherein the analyzed video frames are compressed only after the corresponding feature values have been determined;

storing the compressed digital video sequence in a processor-accessible memory;

using a processor, only after storing the compressed digital video sequence, to automatically analyze the feature values, without decompressing the stored compressed digital video sequence, to identify one or more key video snippets, each key video snippet corresponding to a set of video frames from the digital video sequence;

assembling the key video snippets to form a video summary; and

storing a representation of the video summary in a processor-accessible memory.

2. The method of claim 1 further including using a processor to automatically analyze at least one of the audio samples in the digital video sequence at the time the digital video sequence is captured to determine one or more feature values.

3. The method of claim 1 further including using a processor to automatically analyze at least one of the digital video capture device settings at the time the digital video is captured to determine one or more feature values.

4. The method of claim 1 further including using a processor to automatically analyze data generated by an accelerometer at the time the digital video is captured to determine one or more feature values.

5. The method of claim 1 wherein the determined feature values are stored in the processor-accessible memory as metadata associated with the stored compressed digital video sequence.

6. The method of claim 1 wherein the determined feature values are stored in the processor-accessible memory as a separate file associated with the stored compressed digital video sequence.

7. The method of claim 1 wherein the step of automatically analyzing the feature values further includes identifying one or more key video snippets as a function of user input.

8. The method of claim 1 wherein storing a representation of the video summary in a processor-accessible memory further includes decompressing at least part of the stored compressed digital video sequence to extract video frames corresponding to the video summary, and compressing the extracted video frames to form a compressed video summary, and storing the compressed video summary in a processor-accessible memory.

9. The method of claim 8 further including extracting audio samples corresponding to the video summary and including the extracted audio samples in the compressed video summary.

10. The method of claim 8 wherein the extracted video frames are re-sampled to produce extracted video frames at a different spatial resolution.

11. The method of claim 1 wherein the stored representation of the video summary is a digital video file stored in a format adapted to be played using a standard video player.

12. The method of claim 1 wherein storing a representation of the video summary in a processor-accessible memory further includes generating metadata providing an indication of the video frames in the digital video sequence corresponding to the video summary, and wherein the metadata is stored in association with the stored compressed digital video sequence.

13. A method for forming a video summary for a digital video sequence captured with a digital video capture device, comprising:

capturing a digital video sequence with the digital video capture device, wherein the digital video sequence includes a plurality of video frames;

using a processor to automatically analyze at least one of the video frames in the digital video sequence at the time the digital video sequence is captured to determine one or more feature values;

compressing the digital video sequence, wherein the analyzed video frames are compressed only after the corresponding feature values have been determined;

storing the compressed digital video sequence in a processor-accessible memory;

using a processor, only after storing the compressed digital video sequence, to automatically analyze the feature values, along with additional information contained in the stored compressed digital video sequence, to identify one or more key video snippets, each key video snippet corresponding to a set of video frames from the digital video sequence;

assembling the key video snippets to form a video summary; and

storing a representation of the video summary in a processor-accessible memory.

14. The method of claim 13 wherein a processor is used to automatically analyze the feature values along with audio information contained in the stored compressed digital video sequence, to identify one or more key video snippets, each key video snippet corresponding to a set of video frames from the digital video sequence.

15. The method of claim 13 wherein a processor is used to automatically analyze the feature values along with video information contained in the stored compressed digital video sequence, to identify the one or more key video snippets.

16. A method for forming a video summary for a digital video sequence captured with a digital video capture device, comprising:

a) capturing a digital video sequence with the digital video capture device, wherein the digital video sequence includes a plurality of video frames;

b) using a processor to automatically analyze at least one of the video frames in the digital video sequence at the time the digital video sequence is captured to determine one or more feature values;

c) compressing the digital video sequence, wherein the analyzed video frames are compressed only after the corresponding feature values have been determined;

d) storing the compressed digital video sequence in a processor-accessible memory;

e) using a processor, only after storing the compressed digital video sequence, to automatically analyze the feature values, without decompressing the stored compressed digital video sequence, to identify one or more key video snippets, each key video snippet corresponding to a set of video frames from the digital video sequence;

f) assembling the key video snippets to form a video summary;

g) allowing a user to preview the video summary;

h) receiving adjusted user settings from the user;

i) using a processor to automatically analyze the feature values, without decompressing the stored compressed digital video sequence, to identify one or more updated key video snippets responsive to the adjusted user settings, each updated key video snippet corresponding to a set of video frames from the digital video sequence;

j) assembling the updated key video snippets to form an updated video summary; and

k) storing a representation of the updated video summary in a processor-accessible memory.

17. The method of claim 16 wherein steps g)-j) are repeated until the user is satisfied with the previewed video summary.