METHOD AND APPARATUS FOR PROCESSING VIDEO IMAGE

• US 20160277779A1
• Filed: 10/30/2014
• Published: 09/22/2016
• Est. Priority Date: 12/04/2013
• Status: Active Grant

• Current Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Original Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Inventors: SHAO, Dandan, ZHANG, Jing, XU, Zhenhua
• Granted Patent: US 9,973,793 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04N 21/234381 by altering the temporal resolution, e.g. decreasing the frame rate by frame skipping
• CPC Class Codes: H04N 21/41407 embedded in a portable device, e.g. video client on a mobile phone, PDA, laptop constructional details of equipment or arrangements specially adapted for portable computer application G06F1/1626; arrangements specially adapted for mobile receivers in broadcast systems H04H20/57
• CPC Class Codes: H04N 21/4302 Content synchronisation processes, e.g. decoder synchronisation
• CPC Class Codes: H04N 21/4332 by placing content in organized collections, e.g. local EPG data repository interfaces, Database management systems or updating for information retrieval G06F16/23; details of retrieval of video data and associated meta data in video database G06F16/739
• CPC Class Codes: H04N 21/4333 Processing operations in response to a pause request
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/4884 for displaying subtitles
• CPC Class Codes: H04N 21/6131 involving transmission via a mobile phone network wireless downlink channel access H04W74/006

Abstract

Provided are a method and an apparatus for processing a video image. The method for processing a video image comprises: acquiring information of a current video; intercepting key images of the current video according to the information of the current video, each key image comprising a video frame image with a complete subtitle; sequencing the key images to generate an image library; and receiving a playing request, and according to the playing request, reading, from the image library, corresponding key images for playing.

Claims

1. A method for processing a video image, comprising:

acquiring information of a current video;

intercepting key images of the current video according to the information of the current video, wherein each key image comprises a video frame image having a complete subtitle;

sequencing the key images to generate an image library; and

receiving a playing request, and reading corresponding key images from the image library according to the playing request for playing.

2. The method according to claim 1, wherein intercepting key images of the current video according to the information of the current video comprises:

acquiring a time point sequence of a key subtitle according to the information of the current video; and

intercepting the key images of the current video correspondingly according to the time point sequence of the key subtitle.

3. The method according to claim 2, after acquiring a time point sequence of a key subtitle according to the information of the current video and before intercepting the key images of the current video correspondingly according to the time point sequence of the key subtitle, further comprising:

determining whether a lime interval between two adjacent time points of the key subtitle is greater than a preset period, if yes, acquiring a new time point between the two adjacent time points of the key subtitle and inserting the new time point into the time point sequence of the key subtitle; and

/or

performing an offset correction on a time point of the key subtitle in the time point sequence of the key subtitle.

4. The method according to claim 2, wherein acquiring a time point sequence of key subtitle according to the information of the current video comprises:

acquiring a time range sequence of a subtitle according to a subtitle document of the current video, and generating the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

performing speech recognition on the current video to acquire a time range sequence of a subtitle, and generating the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

converting the current video into video frames, identifying a video frame sequence having a complete subtitle in a preset area in an image recognition way, performing de-duplication on the video frame sequence, and using time points corresponding to a de-duplicated video frame sequence as the time point sequence of the key subtitle.

5. The method according to claim 1, wherein receiving a playing request, and reading corresponding key images from the image library according to the playing request for playing comprises:

receiving an automatic playing request, and reading corresponding key images in sequence from the image library according to the automatic playing request for playing;

or

receiving a calling request, and reading corresponding key images from the image library according to the calling request for playing.

6. The method according to claim 5, after reading corresponding key images from the image library according to the calling request for playing, further comprising:

receiving a stop playing request, and stopping reading the corresponding key images from the image library according to the stop playing request.

7. An apparatus for processing a video image, comprising:

an acquiring module, configured to acquire information of a current video;

an intercepting module, configured to intercept key images of the current video according to the information of the current video acquired by the acquiring module, wherein each key image comprises a video frame image having a complete subtitle;

a generating module, configured to sequence the key images intercepted by the intercepting module to generate an image library; and

a playing module, configured to receive a playing request, and read corresponding key images from the image library generated by the generating module according to the playing request for playing.

8. The apparatus according to claim 7, wherein the intercepting module comprises:

a time point sequence acquiring unit, configured to acquire a time point sequence of a key subtitle according to the information of the current video; and

an intercepting unit, configured to intercept the key images of the current video correspondingly according to the time point sequence of the key subtitle.

9. The apparatus according to claim 8, wherein the intercepting module further comprises a frame adding unit and a correcting unit which are located between the time point sequence acquiring unit and the intercepting unit, wherein:

the frame adding unit is configured to determine whether a time interval between two adjacent time points of the key subtitle in the time point sequence of the key subtitle acquired by the time point sequence acquiring unit or corrected by the correcting unit is greater than a preset period, if yes, to acquire a new time point between the two adjacent time points of the key subtitle and to insert the new time point into the time point sequence of the key subtitle; and

/or

the correcting unit is configured to perform an offset correction on a time point of the key subtitle in the time point sequence of the key subtitle acquired by the time point sequence acquiring unit or by the frame adding unit.

10. The apparatus according to claim 8, wherein the time point sequence acquiring unit is specifically configured to:

acquire a time range sequence of a subtitle according to a subtitle document of the current video, and generate the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

perform speech recognition on the current video to acquire a time range sequence of subtitles, and generate the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

convert the current video into video frames, identify a video frame sequence having a complete subtitle in a preset area in an image recognition way, perform de-duplication on the video frame sequence, to use time points corresponding to a de-duplicated video frame sequence as the time point sequence of the key subtitle.

11. The apparatus according to claim 7, wherein the playing module is specifically configured to:

receive an automatic playing request, and read corresponding key images in sequence from the image library according to the automatic playing request for playing;

or

receive a calling request, and read corresponding key images from the image library according to the calling request for playing.

12. The apparatus according to claim 11, wherein the playing module is further configured to:

receive a stop playing request and stop reading the corresponding key images from the image library according to the stop playing request, after corresponding key images are read from the image library according to the calling request for playing.

13. A storage medium for storing an application, wherein the application is configured to execute a method for processing a video image, the method comprising:

acquiring information of a current video;

intercepting key images of the current video according to the information of the current video, wherein each key image comprises a video frame image having a complete subtitle;

sequencing the key images to generate an image library; and

receiving a playing request, and reading corresponding key images from the image library according to the playing request for playing.

14. The method according to claim 3, wherein acquiring a time point sequence of key subtitle according to the information of the current video comprises:

acquiring a time range sequence of a subtitle according to a subtitle document of the current video, and generating the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

performing speech recognition on the current video to acquire a time range sequence of a subtitle, and generating the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

converting the current video into video frames, identifying a video frame sequence having a complete subtitle in a preset area in an image recognition way, performing de-duplication on the video frame sequence, and using time points corresponding to a de-duplicated video frame sequence as the time point sequence of the key subtitle.

15. The apparatus according to claim 9, wherein the time point sequence acquiring unit is specifically configured to:

acquire a time range sequence of a subtitle according to a subtitle document of the current video, and generate the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

perform speech recognition on the current video to acquire a time range sequence of subtitles, and generate the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

convert the current video into video frames, identify a video frame sequence having a complete subtitle in a preset area in an image recognition way, perform de-duplication on the video frame sequence, to use time points corresponding to a de-duplicated video frame sequence as the time point sequence of the key subtitle.

16. The storage medium according to claim 13, wherein intercepting key images of the current video according to the information of the current video comprises:

acquiring a time point sequence of a key subtitle according to the information of the current video; and

intercepting the key images of the current video correspondingly according to the time point sequence of the key subtitle.

17. The storage medium according to claim 13, wherein after acquiring a time point sequence of a key subtitle according to the information of the current video and before intercepting the key images of the current video correspondingly according to the time point sequence of the key subtitle, the method further comprises:

determining whether a time interval between two adjacent time points of the key subtitle is greater than a preset period, if yes, acquiring a new time point between the two adjacent time points of the key subtitle and inserting the new time point into the time point sequence of the key subtitle; and

/or

performing an offset correction on a time point of the key subtitle in the time point sequence of the key subtitle.

18. The storage medium according to claim 13, wherein acquiring a time point sequence of key subtitle according to the information of the current video comprises:

acquiring a time range sequence of a subtitle according to a subtitle document of the current video, and generating the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

performing speech recognition on the current video to acquire a time range sequence of a subtitle, and generating the time point sequence of the key subtitle according to the time range sequence of the subtitle;

or

converting the current video into video frames, identifying a video frame sequence having a complete subtitle in a preset area in an image recognition way, performing de-duplication on the video frame sequence, and using time points corresponding to a de-duplicated video frame sequence as the time point sequence of the key subtitle.

19. The storage medium according to claim 13, wherein receiving a playing request, and reading corresponding key images from the image library according to the playing request for playing comprises:

receiving an automatic playing request, and reading corresponding key images in sequence from the image library according to the automatic playing request for playing;

or

receiving a calling request, and reading corresponding key images from the image library according to the calling request for playing.

20. The storage medium according to claim 13, after reading corresponding key images from the image library according to the calling request for playing, the method further comprises:

receiving a stop playing request, and stopping reading the corresponding key images from the image library according to the stop playing request.