Information processing apparatus and method of controlling same

• US 8,270,806 B2
• Filed: 10/22/2009
• Issued: 09/18/2012
• Est. Priority Date: 10/29/2008
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Tojo, Hiroshi, Sohma, Hidetomo, Yashiro, Satoshi
• Primary Examiner(s): Tran, Thai
• Assistant Examiner(s): Dunn, Mishawn
• Application Number:
  US12/604,058
• Publication Number:
  US 20100104266A1
• Time in Patent Office: 1,062 Days
• Field of Search: 386/239, 386/241, 386/326, 386/353, 348/700, 382/118
• US Class Current: 386/241
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks
• CPC Class Codes: H04N 5/782 on tape

Abstract

An information processing apparatus for extracting a more appropriate representative frame image from moving image data that includes a plurality of frames of image data arranged in a time series includes: an input unit configured to input moving image data; a detecting unit configured to detect a frame image, which includes an image similar to a prescribed image pattern; a tracking unit configured to detect a frame image, which includes an image similar to the image included in the detected frame image; a storage unit configured to store successive frame images that have been detected by the tracking unit; a splitting unit configured to split the moving image data into a plurality of time intervals; and an extracting unit configured to extract a representative frame image using different evaluation rules.

Claims

1. An information processing apparatus comprising:

an input unit configured to input moving image data that includes a plurality of frame images arranged in a time series;

a detecting unit configured to detect a frame image, which includes an image similar to a prescribed subject pattern, from moving image data that has been input;

a tracking unit configured to detect a frame image, which includes an image similar to the image included in the frame image detected by said detecting unit, detection being performed by adopting frame images before and after the detected frame image as a target;

a storage unit configured to store, as a subject sequence, successive frame images that have been detected by said tracking unit, the successive images being stored in association with time information in the moving image data corresponding to the subject sequence;

a splitting unit configured to split the moving image data into subject intervals, each of which includes one or more subject sequences and non-subject intervals, each of which includes no subject sequences; and

a first extracting unit configured to extract, from each of the subject intervals, a first representative frame image using a first evaluation rule; and

a second extracting unit configured to extract, from each of the non-subject intervals, a second representative frame image using a second evaluation rule which is different from the first evaluation rule.

2. The apparatus according to claim 1, wherein said first extracting unit calculates, based upon the first evaluation rule, an evaluation value of each of the frame images included in each of the subject intervals, and extracts a frame image, for which the evaluation value is maximum or minimum, as the first representative frame image in the subject interval.

3. The apparatus according to claim 1, wherein said second extracting unit derives a motion vector distribution between frame images included in non-subject intervals, calculates each evaluation value of the frame images based upon the derived motion vector distribution and extracts a frame image, for which the evaluation value is maximum or minimum, as the first representative frame image in the subject interval.

4. The apparatus according to claim 1, wherein the prescribed subject pattern is a face image of a person.

6. A non-transitory computer-readable recording medium retrievably storing a computer program for causing a computer to function as each of the units of the information processing apparatus set forth in claim 1.

5. A method of controlling an information processing apparatus for extracting one or more representative frame images from moving image data, said method comprising:

an input step of inputting moving image data that includes a plurality of frame images arranged in a time series;

a detecting step of detecting a frame image, which includes an image similar to a prescribed subject pattern, from moving image data that has been input;

a tracking step of detecting a frame image, which includes an image similar to the image included in the frame image detected at said detecting step, detection being performed adopting frame images before and after the detected frame image as a target;

a storage step of storing, as a subject sequence, successive frame images that have been detected at said tracking step, the successive images being stored in a storage unit in association with time information in the moving image data corresponding to the subject sequence;

a splitting step of splitting the moving image data into subject intervals, each of which includes one or more subject sequences and non-subject intervals, each of which includes no subject sequences; and

a first extracting step of extracting, from each of the subject intervals, a first representative frame image using a first evaluation rule; and

a second extracting step of extracting, from each of the non-subject intervals, a second representative frame image using a second evaluation rule which is different from the first evaluation rule.