System for facilitating the search of video content

• US 8,611,701 B2
• Filed: 05/21/2008
• Issued: 12/17/2013
• Est. Priority Date: 05/21/2008
• Status: Active Grant

• Current Assignee: ZTE Corporation
• Original Assignee: Yuvad Technologies Co. Ltd
• Inventors: Zhang, Ji
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US12/085,827
• Publication Number:
  US 20100265390A1
• Time in Patent Office: 2,036 Days
• Field of Search: 382/100, 382/305, 707769-780, 707/799.003
• US Class Current: 382/305
• CPC Class Codes: G06F 16/70 of video data
• 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: H04N 21/23109 by placing content in organized collections, e.g. EPG data repository details of retrieval of video data and associated meta data in video databases G06F16/739
• CPC Class Codes: H04N 21/26603 for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques
• CPC Class Codes: H04N 21/2665 Gathering content from different sources, e.g. Internet and satellite
• CPC Class Codes: H04N 21/4828 for searching program descriptors retrieval of video data G06F16/739

Abstract

A system for facilitating the search of video content, comprising a fingerprint extractor which is adapted to extract a fingerprint associated with a video content clip for specific time of video content; a fingerprint archive database from which database entries matching the specific time of video content are selected; a search module to which the database entries matching the specific time of video content are delivered, by which the searched database entries into continuous fingerprint streams are reconstructed, and in which the searched database entries from the same location and channel are grouped together, and the fingerprint data sections are stripped out of the entries and concatenated according to the segment ID and time-stamps contained within each entry; a matcher by which the fingerprint associated with the video clip is searched from the continuous fingerprint streams to find a match; and a formatter which is adapted to combine a matching result with additional information obtained from the archive entries to form a search report. The system according to the present invention can extract fingerprint information from video content for the purpose of archiving without the huge storage capacity required, can collect statistics and extract additional information from the archived video information automatically based on the user entered searching video clip information, and can search through video fingerprint data for identifying historical recording and collect statistics and extract additional information of video content easily at low hardware cost.

Claims

1. A system for facilitating the search of video content, comprising

a fingerprint extractor which is adapted to extract image samples from a plurality of digital frames of a video content clip for specific time duration;

the said fingerprint extractor forms groups of data associated with each of the said video frame;

the said fingerprint extractor forms fingerprint data from plurality of groups of data associated with a plurality of video frames;

a fingerprint database storing fingerprint data extracted from distributed video content, in which database entries are stored according to specific time duration, location, broadcast channel and type of programming content of the distributed video content;

a search module to which at least one database entry matching the specific time duration of original recording of video content are delivered, by which the searched database entries into continuous fingerprint streams are reconstructed, and in which the searched database entries from the same location and channel are grouped together, and the fingerprint data sections are stripped out of the entries and concatenated according to the segment ID and time-stamps contained within each of the entries;

a matcher by which the fingerprint associated with the video clip is used as query to search from the continuous fingerprint streams to issue a match result if a match has been found; and

a formatter which combines the matching result from the matcher when a match is found with additional information obtained from the fingerprint database comprising time, location, and channel information to form a search report.

2. The system according to claim 1, wherein the additional information obtained from the fingerprint database comprises content types.

3. The system according to claim 1, wherein the video content clip is in digital compressed video data format, and it is made to first go through the receiver converter to perform decompression and deliver the digital decompressed video frames to the fingerprint extractor.

4. The system according to claim 1, wherein the input to the extractor is the digitized video frame data, and it is stored into a frame buffer, and a sub-sampler obtains selected samples from each video frame data to form fingerprint data.

5. The system according to claim 1, wherein said fingerprint data is used as query to search from said fingerprint database according to location, time, and channel when the recording was made, and/or programming content.

6. The system according to claim 1, wherein said fingerprint stream is advanced relative to said searching fingerprint by one frame and the matching operation is repeated, if a match is not found.

7. The system according to claim 6, wherein if a match is found, the additional information associated with the entries is combined with the information on the searching video clip to produce a single report message.

8. The system according to claim 7, wherein the single report message contains channel, video recording time of the start and end frames of the matched fingerprint and geographic locations of the video recording.