Content identification apparatus and content identification method

• US 10,200,765 B2
• Filed: 08/19/2015
• Issued: 02/05/2019
• Est. Priority Date: 08/21/2014
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Inventors: Yabu, Hiroshi
• Primary Examiner(s): Marandi, James R
• Application Number:
  US15/302,460
• Publication Number:
  US 20170026718A1
• Time in Patent Office: 1,266 Days
• Field of Search: None
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/783 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/48 Matching video sequences
• CPC Class Codes: H04N 21/8352 involving content or source identification data, e.g. Unique Material Identifier [UMID]
• CPC Class Codes: H04N 21/8358 involving watermark protecting executable software by watermarking G06F21/16; image watermarking in general G06T1/0021; watermarks inserted in still images for transmission purposes H04N1/32144; inserting watermarks during video coding H04N19/467

Abstract

A recognition data creation device includes: a fingerprint creator; a sorter; and a collator. The fingerprint creator creates fingerprints for each of a plurality of acquired video content candidates. The sorter sorts the video content candidates by using attached information included in recognition data input from an outside. The collator collates the fingerprints of the video content candidates which are sorted by the sorter with fingerprints included in the recognition data, and specifies video content which corresponds to the fingerprints included in the recognition data from among the video content candidates.

Claims

1. A content recognition device comprising:

a fingerprint creator that creates fingerprints for each of a plurality of acquired video content candidates;

a sorter that sorts the video content candidates by using attached information included in recognition data received by the content recognition device; and

a collator that collates the fingerprints of the video content candidates sorted by the sorter with fingerprints included in the recognition data, and specifies video content which corresponds to the fingerprints included in the recognition data from among the video content candidates,

wherein the fingerprint creator creates a static fingerprint based on a static region in which an inter-frame image variation between a plurality of image frames which compose the video content candidates is smaller than a first threshold, creates a dynamic fingerprint based on a dynamic region in which the inter-frame image variation is larger than a second threshold, and associates each of the fingerprints created by the fingerprint creator with type information indicating whether the fingerprint is the static fingerprint or the dynamic fingerprint.

2. The content recognition device according to claim 1,

wherein the fingerprints are classified into at least two types which are a first fingerprint and a second fingerprint;

the recognition data includes, as the attached information, type information indicating the types of the fingerprints; and

the sorter sorts the video content candidates by comparing the type information included in the recognition data with types of the fingerprints of the video content candidates.

3. The content recognition device according to claim 1,

wherein the sorter sorts the video content candidates by comparing a sequence of the attached information included in the recognition data with a sequence of the type information.

4. The content recognition device according to claim 1,

wherein the recognition data includes information indicating a creation time of the fingerprints included in the recognition data;

and

the sorter selects the fingerprints of the video content candidates based on the information indicating the creation time and on a creation time of the fingerprints of the video content candidates.

5. The content recognition device according to claim 4,

wherein the sorter selects a fingerprint which is created at a closest time to the information indicating the creation time included in the recognition data from among the fingerprints of the video content candidates, and sorts the video content candidates based on a comparison between a type of the selected fingerprint and the attached information included in the recognition data.

6. A content recognition device according to claim 1,

wherein the attached information includes geographic information indicating a position of a device that transmits video content serving as a creation source of the recognition data, or a position of a device that transmits the recognition data.

7. The content recognition device according to claim 1, wherein the attached information includes user information stored in a device that transmits the recognition data.

8. A content recognition method comprising:

creating fingerprints for each of a plurality of acquired video content candidates;

receiving recognition data;

sorting the video content candidates by using attached information included in the received recognition data;

collating the fingerprints of the sorted video content candidates with fingerprints included in the recognition data, and specifying video content which corresponds to the fingerprints included in the recognition data from among the video content candidates;

creating a static fingerprint based on a static region in which an inter-frame image variation between a plurality of image frames which compose the video content candidates is smaller than a first threshold;

creating a dynamic fingerprint based on a dynamic region in which the inter-frame image variation is larger than a second threshold; and

associating each of the created fingerprints with type information indicating whether the fingerprint is the static fingerprint or the dynamic fingerprint,

wherein the recognition data includes the attached information indicating whether each of the fingerprints included in the recognition data is the static fingerprint or the dynamic fingerprint, and

the video content candidates are sorted by comparing the attached information included in the recognition data with the type information.

9. A non-transitory computer-readable recording medium storing a computer program to be executed by a computer for performing the content recognition method according to claim 8.