IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND PROGRAM

• US 20140047367A1
• Filed: 06/17/2013
• Published: 02/13/2014
• Est. Priority Date: 08/09/2012
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: NIELSEN, Frank
• Granted Patent: US 9,632,678 B2
• Time in Patent Office: Days
• US Class Current: 715/767
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06F 3/04845 for image manipulation, e.g. dragging, rotation, expansion or change of colour
• CPC Class Codes: G06T 15/20 Perspective computation

Abstract

An image processing apparatus includes: an acquisition section configured to acquire positional information specified by a user on an input image for specifying area selection; and out of a calculation result of a transformation matrix between an object plane being a perspective projection plane formed by an object in the input image and an isothetic plane, a selected-area calculation section configured to calculate an area in the object plane as a selected area by the user using the transformation matrix of the object plane corresponding to the positional information specified by the user.

Claims

1. An image processing apparatus comprising:

an acquisition section configured to acquire positional information specified by a user on an input image for specifying area selection; and

out of a calculation result of a transformation matrix between an object plane being a perspective projection plane formed by an object in the input image and an isothetic plane, a selected-area calculation section configured to calculate an area in the object plane as a selected area by the user using the transformation matrix of the object plane corresponding to the positional information specified by the user.

2. The image processing apparatus according to claim 1, further comprising:

a recognition section configured to recognize the object plane in the input image; and

a transformation matrix calculation section configured to calculate a transformation matrix between the object plane recognized by the recognition section and the isothetic plane.

3. The image processing apparatus according to claim 2,

wherein the recognition section recognizes a convex quadrilateral formed by an object in the input image as the object plane, and

the transformation matrix calculation section calculates a transformation matrix between the convex quadrilateral recognized by the recognition section and a unit square as the isothetic plane.

4. The image processing apparatus according to claim 3,

wherein the recognition section performs area division processing on the input image to extract a contour of the object, and recognizes the convex quadrilateral formed by the object on the basis of the extracted contour.

5. The image processing apparatus according to claim 1, further comprising a hierarchical structure building section configured to build a hierarchical structure of a plurality of the object planes,

wherein the selected-area calculation section calculates an area in the object plane as the selected area by the user using the transformation matrix of the object plane having a predetermined hierarchy corresponding to the positional information specified by the user.

6. The image processing apparatus according to claim 5,

wherein the selected-area calculation section uses the transformation matrix of the object plane having a lowest level corresponding to the positional information specified by the user.

7. The image processing apparatus according to claim 1, further comprising a display control section configured to display the object plane corresponding to the positional information specified by the user.

8. The image processing apparatus according to claim 7,

wherein the display control section displays the object plane corresponding to the positional information specified by the user in accordance with area-selection specification operation by the user, and deletes the object plane after passage of a predetermined time period.

9. The image processing apparatus according to claim 1,

wherein the acquisition section acquires at least two points specified by the user on the input image as the positional information.

10. The image processing apparatus according to claim 9,

wherein the acquisition section acquires the two points in a diagonal direction, specified by the user, on the input image as the positional information, and

the selected-area calculation section calculates two points other than the two points in the diagonal direction, specified by the user, using the transformation matrix out of four points forming the convex quadrilateral as the object plane.

11. The image processing apparatus according to claim 1,

wherein the transformation matrix is a homography matrix and a homography inverse matrix being an inverse matrix thereof.

12. The image processing apparatus according to claim 1, further comprising an image edit section configured to perform swap processing for swapping a first area image being the selected area by the user, calculated on the basis of a first piece of the positional information, and a second area image being the selected area by the user, calculated on the basis of a second piece of the positional information.

13. A method of processing an image, the method comprising:

acquiring positional information specified by a user on an input image for specifying area selection; and

out of a calculation result of a transformation matrix between an object plane being a perspective projection plane formed by an object in the input image and an isothetic plane, calculating an area in the object plane as a selected area by the user using the transformation matrix of the object plane corresponding to the positional information specified by the user.

14. A program for causing a computer to perform processing comprising:

acquiring positional information specified by a user on an input image for specifying area selection; and

out of a calculation result of a transformation matrix between an object plane being a perspective projection plane formed by an object in the input image and an isothetic plane, calculating an area in the object plane as a selected area by the user using the transformation matrix of the object plane corresponding to the positional information specified by the user.