Granted Patent B2

US 9,542,604 · App. 14/710,824 · Granted Jan 10, 2017

Abstract

Claims (48)

1. A method of providing a combined summary in a video reproducing apparatus, the method comprising:

receiving audio and video captured by at least one camera;

generating a video summary by detecting at least one video event from at least one of the audio and the video;

generating an audio summary by detecting at least one audio event from at least one of the audio and the video;

extracting at least one section of the video summary corresponding to the at least one audio event, and storing the extracted at least one section of the video summary with the audio summary; and

providing a display of the video reproducing apparatus with a video summary control interface for controlling the video summary and an audio summary control interface for controlling the audio summary.

2. The method of claim 1 , further comprising:

selecting a section of the video summary, in which a specific video event is detected, using the video summary control interface;

selecting a section of the audio summary, in which a specific audio event is detected, using the audio summary control interface; and

if the selected section of the video summary and the selected section of the audio summary overlap with each other, identifying the overlapping sections to be distinguished from the other sections of the video summary and the audio summary, in the display of the video reproducing apparatus.

3. The method of claim 1 , further comprising:

selecting a section of the audio summary, in which a specific audio event is detected, using the audio summary control interface; selecting a section of the video summary, in which a specific video event is detected, using the video summary control interface; and

if the selected section of the audio summary and the selected section of the video summary overlap with each other, identifying the overlapping sections to be distinguished from the other sections, in the display of the video reproducing apparatus.

4. The method of claim 1 , further comprising reproducing at least one of the audio summary and the video summary.

5. The method of claim 1 , wherein the at least one audio event is detected from the at least one of the audio and the video by determining that the at least one audio event has occurred if an identifiable feature is detected from the at least one of the audio and the video, and

wherein the identifiable feature comprises at least one of a specific word, a specific character, and specific sound.

6. The method of claim 5 , wherein the generating the audio summary comprises:

determining a time range corresponding to the detected at least one audio event;

determining if the identifiable feature satisfies a preset condition;

increasing the time range by a predetermined amount before and after the detected at least one audio event, if the identifiable feature does not satisfy the preset condition; and

extracting an audio frame corresponding to the increased time range to generate the audio summary.

7. The method of claim 5 , further comprising:

converting the identifiable feature into a text; and

displaying the text in the audio summary with time information about when the identifiable feature is detected.

8. The method of claim 7 , further comprising:

selecting the text displayed in the audio summary using the audio summary control interface; and

as a result of the selecting, detecting at least one audio section constituting the audio summary and the at least one section of the video summary which corresponds to the at least one audio section.

9. The method of claim 7 , further comprising providing the identifiable feature converted into the text in the form of tag in the audio summary.

10. The method of claim 5 , wherein the specific sound is detected from the audio based on frequency characteristics.

11. The method of claim 5 , further comprising receiving an input frequency characteristic value through the audio summary control interface; and

detecting sound which matches the input frequency characteristic value as the specific sound.

12. The method of claim 11 , wherein the audio summary control interface supports a sound selection interface for selecting or inputting the input frequency characteristic value, and

wherein the sound selection interface provides an interface for selecting at least one among a woman, a man, an infant, the old, high-pitch sound, low-pitch sound, and an emergency state, based on the input frequency characteristic value.

13. A video reproducing apparatus for providing a combined summary, the apparatus comprising:

a receiver configured to receive audio and video captured by at least one camera;

a video summary generator configured to generate a video summary by detecting at least one video event from at least one of the audio and video;

an audio summary generator configured to generate an audio summary by detecting at least one event from at least one of the audio and the video;

an audio summary storage configured to extract at least one section of the video summary corresponding to the at least one audio event, and store the extracted at least one section of the video summary with the audio summary; and

a video summary control interface provided for controlling the video summary on a display of the video reproducing apparatus; and

an audio summary control interface provided for controlling the audio summary on the display of the video reproducing apparatus.

14. The apparatus of claim 13 , wherein the audio summary generator is further configured to detect the at least one audio event from the at least one of the audio and the video by determining that the at least one audio event has occurred if an identifiable feature is detected from the at least one of the audio and the video, and

wherein the identifiable feature comprises at least one of a specific word, a specific character, and specific sound.

15. The apparatus of claim 14 , further comprising a text converter configured to covert the identifiable feature into a text and display the text in the audio summary with time information about when the identifiable feature is detected.

16. The apparatus of claim 15 , wherein the audio summary control interface is configured to allow selection of the text displayed in the audio summary, and

as a result of the selection, the audio summary generator is configured to detect at least one audio section constituting the audio summary and the at least one section of the video summary which corresponds to the at least one audio section.

17. The apparatus of claim 14 , wherein the audio summary generator is further configured to receive an input frequency characteristic value through the audio summary control interface, and detect sound which matches the input frequency characteristic value as the specific sound.

18. The apparatus of claim 13 , wherein the audio summary generator comprises an audio frame extractor, and

wherein the audio frame extractor is configured to determine a time range corresponding to the detected at least one audio event, determine if the identifiable feature satisfies a preset condition, increase the time range by a predetermined amount before and after the detected at least one audio event, if the identifiable feature does not satisfy the preset condition, and extract an audio frame corresponding to the increased time range to generate the audio summary.

Assignments (6)