IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND PROGRAM

• US 20100104256A1
• Filed: 09/23/2009
• Published: 04/29/2010
• Est. Priority Date: 10/27/2008
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: TSURUMI, Shingo
• Granted Patent: US 8,368,815 B2
• Time in Patent Office: Days
• US Class Current: 386/241
• CPC Class Codes: G06V 40/175 Static expression
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• 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: G11B 27/322 used signal is digitally coded

Abstract

An image processing apparatus includes: a calculating unit configured to calculate motion information relating to between two images that make up an imaged moving picture; and a selecting unit configured to select compositing target images serving as compositing targets from a plurality of images that make up the imaged moving picture based on reliability that indicates the likelihood of the calculated motion information.

Claims

1. An image processing apparatus comprising:

a calculating unit configured to calculate motion information relating to between two images that make up an imaged moving picture; and

a selecting unit configured to select compositing target images serving as compositing targets from a plurality of images that make up said imaged moving picture based on reliability that indicates the likelihood of said calculated motion information.

2. The image processing apparatus according to claim 1, said selecting unit comprising:

a section selecting unit configured to select a section used for selecting said compositing target images from a plurality of images that make up said imaged moving picture based on said reliability; and

an image selecting unit configured to select said compositing target images from a plurality of images included in said selected section based on relative position relationship of images included in said selected section.

3. The image processing apparatus according to claim 2, wherein, in the case that said selected compositing target images are taken as reference images, and a target image that is another image included in said selected section, and said reference images have been each converted with said motion information, said image selecting unit selects a new compositing target image based on the overlaying rate between said target image and said reference images.

4. The image processing apparatus according to claim 2, further comprising:

a determining unit configured to determine the attributes of a target included in said image;

wherein said image selecting unit selects said compositing target images based on said determined attributes.

5. The image processing apparatus according to claim 4, wherein said image selecting unit calculates an evaluated value based on said determined attributes for each of targets included in said image, and selects said compositing target images based on the evaluated value calculated for each of said targets.

6. The image processing apparatus according to claim 5, wherein said image selecting unit takes said selected compositing target images as reference images, and selects a new compositing target image based on said evaluated value calculated for each of targets included in a target image that is another image included in said selected section, and said evaluated value calculated for each of targets included in said reference images.

7. The image processing apparatus according to claim 2, wherein said section selecting unit selects a section including an image of a certain range as said section.

8. The image processing apparatus according to claim 2, further comprising:

a reliability determination score calculating unit configured to calculate a reliability determination score that indicates a score used for determining said reliability based on said calculated motion information;

wherein said motion information includes components relating to enlargement/reduction, translational movement, and rotation;

and wherein said section selecting unit selects said section based on said calculated reliability determination score, said translational component, said rotational component, and said enlargement/reduction component that relate to said motion information.

9. The image processing apparatus according to claim 8, said calculating unit comprising:

a feature point extracting unit configured to extract, based on pixels included in a first image that makes up said imaged moving picture, a feature point of said first image;

a motion amount calculating unit configured to calculate the motion amount of a second image that is an image following said first image that makes up said imaged moving picture as to said first image based on each of said extracted feature points; and

a motion information calculating unit configured to calculate said motion information based on said calculated motion amount;

wherein said reliability determination score calculating unit calculates a value that indicates the rate of a feature point that exhibits dominant motion at the time of calculating said motion information by said motion information calculating unit, of said extracted feature points, as said reliability determination score.

10. The image processing apparatus according to claim 8, wherein, with a first image that makes up said imaged moving picture as a reference, in the case that a second image that is an image following said first image that makes up said imaged moving picture is converted based on said motion information, said reliability determination score calculating unit calculates the luminance difference value of pixels at an overlaid region of said first image and said second image, and calculates said reliability determination score based on the difference value thereof.

11. The image processing apparatus according to claim 10, said calculating unit comprising:

a feature point extracting unit configured to extract a feature point of said first image based on each of pixels included in said first image;

a motion amount calculating unit configured to calculate the motion amount of said second image as to said first image based on each of said extracted feature points; and

a motion information calculating unit configured to calculate said motion information based on said calculated motion amount;

wherein said reliability determination score calculating unit calculates, of said feature points extracted in said overlaid region, the luminance difference value of pixels around a feature point that exhibits dominant motion at the time of calculating said motion information by said motion information calculating unit, and calculates said reliability determination score based on the difference value thereof.

12. An image processing method comprising the steps of:

calculating motion information relating to between two images that make up an imaged moving picture; and

selecting of compositing target images serving as compositing targets from a plurality of images that make up said imaged moving picture based on reliability that indicates the likelihood of said calculated motion information.

13. A program causing a computer to execute:

calculating of motion information relating to between two images that make up an imaged moving picture; and

selecting of compositing target images serving as compositing targets from a plurality of images that make up said imaged moving picture based on reliability that indicates the likelihood of said calculated motion information.