Information processing apparatus, information processing method, and storage medium

• US 10,262,199 B2
• Filed: 01/15/2014
• Issued: 04/16/2019
• Est. Priority Date: 01/17/2013
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Anabuki, Mahoro, Katano, Yasuo, Matsugu, Masakazu, Suzuki, Masahiro
• Primary Examiner(s): Thomas, Mia M
• Application Number:
  US14/156,337
• Publication Number:
  US 20140198962A1
• Time in Patent Office: 1,917 Days
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

In order to reduce limitations on an arrangement of a posture visualization system as a whole, a posture recognition unit recognizes, based on image data of a real space captured by an image capture unit from a predetermined viewpoint, a posture of an object in the image data of the real space. A posture visualization viewpoint setting unit sets a viewpoint different from the predetermined viewpoint. A posture visualization unit visualizes a mirror image of the posture of the object viewed from the viewpoint set by the posture visualization viewpoint setting unit based on the posture recognized by the posture recognition unit. A space display unit displays the mirror image of the posture of the object generated by the posture visualization unit and a mirror image of the real space at once.

Claims

1. An image processing apparatus comprising:

a recognition unit configured to recognize, based on a first image captured by an image capture unit from a first viewpoint, a posture of an object in the first image;

a setting unit configured to set a second viewpoint for displaying a space virtually including the object and a third viewpoint to see the posture of the object, based on the posture of the object recognized by the recognition unit;

a generation unit configured to generate, at the time at which the first image was captured by the image capture unit, a second image of the space in which the posture of the recognized object is located as a visualization of a model of the object being viewed from a virtual camera at the second viewpoint, and a third image of the posture of the object as a visualization of the model of the object being viewed from another virtual camera at the third viewpoint; and

a display control unit configured to display the second image of the space and the third image of the recognized posture of the object generated by the generation unit on a display unit.

2. The image processing apparatus according to claim 1, wherein the display control unit flips displays the image of the space and the image of the posture of the object viewed from the third viewpoint generated by the generation unit as a mirror reversed image left side right and displays the resultant images on the display unit.

3. The image processing apparatus according to claim 1,

wherein the generation unit, based on posture data indicating a reference posture, generates the reference posture viewed from the third viewpoint, and

wherein the display control unit further displays the reference posture viewed from the third viewpoint generated by the generation unit on the display unit.

4. The image processing apparatus according to claim 3 further comprising a comparison unit configured to compare the posture of the object viewed from the third viewpoint and the reference posture viewed from the third viewpoint,

wherein the display control unit further displays a comparison result of the comparison unit on the display unit.

5. The image processing apparatus according to claim 1 further comprising a recording unit configured to record a result obtained by the generation unit,

wherein the display control unit displays the result recorded in the recording unit on the display unit.

6. The image processing apparatus according to claim 1, wherein the first viewpoint, the second viewpoint, and the third viewpoint are different from each other.

7. An image processing method performed by an image processing apparatus, the image processing method comprising:

recognizing, based on a first image captured by an image capture unit from a first viewpoint, a posture of an object in the first image;

setting a second viewpoint for displaying a space virtually including the object and a third viewpoint to see the posture of the object, based on the posture of the recognized object;

generating, at the time at which the first image was captured by the image capture unit, a second image of the space in which the recognized posture of the object is located as a visualization of a model of the object being viewed from a virtual camera at the second viewpoint, and, a third image of the recognized posture of the object being viewed from another virtual camera at the third viewpoint; and

performing a display control so that the generated second image of the space and the generated third image of the recognized posture of the object are displayed on a display unit.

8. A non-transitory storage medium storing a program having computer executable instructions, upon execution cause a computer to perform:

recognizing, based on a first image captured by an image capture unit from a first viewpoint, a posture of an object in the first image;

setting a second viewpoint for displaying a space virtually including the object and a third viewpoint to see the posture of the object, based on the posture of the recognized object;

generating, at the time at which the first image was captured by the image capture unit, a second image of the space in which the recognized posture of the object is located as a visualization of a model of the object being viewed from a virtual camera at the second viewpoint, and, a third image of the recognized posture of the object being viewed from another virtual camera at the third viewpoint; and

performing a display control so that the generated second image of the space and the generated third image of the recognized posture of the object are displayed on a display unit.