IMAGE PROCESSING APPARATUS AND METHOD, AND PROGRAM

• US 20120020550A1
• Filed: 06/09/2011
• Published: 01/26/2012
• Est. Priority Date: 07/21/2010
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: ZHOU, Ning
• Granted Patent: US 8,873,800 B2
• Time in Patent Office: Days
• US Class Current: 382/155
• CPC Class Codes: G06V 40/107 Static hand or arm

Abstract

The present disclosure provides an image processing apparatus, including: a recognition section adapted to recognize, based on a learning result obtained by learning of a learning image regarding a predetermined object, the object in a predetermined frame of an input image formed from a plurality of frames which are continuous in time; and a setting section adapted to set a parameter to be used for a process to be carried out for a later frame which is later in time than the predetermined frame of the input image in response to a difference in image information between an object image, which is an image in a region of the object recognized in the predetermined frame, and the learning image; the recognition section recognizing the object in the later frame for which the process is carried out based on the parameter set by the setting section.

Claims

1. An image processing apparatus, comprising:

a recognition section adapted to recognize, based on a learning result obtained by learning of a learning image regarding a predetermined object, the object in a predetermined frame of an input image formed from a plurality of frames which are continuous in time; and

a setting section adapted to set a parameter to be used for a process to be carried out for a later frame which is later in time than the predetermined frame of the input image in response to a difference in image information between an object image, which is an image in a region of the object recognized in the predetermined frame, and the learning image;

said recognition section recognizing the object in the later frame for which the process is carried out based on the parameter set by said setting section.

2. The image processing apparatus according to claim 1, further comprising a processing section adapted to carry out a predetermined image process for the input image;

said setting section setting an image processing parameter to be used in an image process carried out for the later frame by said processing section in response to the difference in image information between the object image and the learning image;

said processing section carrying out the image process for the later frame based on the image processing parameter set by said setting section;

said recognition section recognizing the object in the later frame for which the image process is carried out by said processing section.

3. The image processing apparatus according to claim 1, wherein said setting section sets a recognition processing parameter to be used in a recognition process to be carried out for the later frame by said recognition section in response to the difference in image information between the object image and the learning image;

said recognition section recognizing the object in the later frame based on the recognition processing parameter set by said setting section.

4. The image processing apparatus according to claim 1, further comprising an image pickup section adapted to pick up an image of an image pickup object to acquire the input image;

said setting section setting an image pickup parameter relating to image pickup by said image pickup section in response to the difference in image information between the object image and the learning image in the predetermined frame;

said image pickup section acquiring the input image based on the image pickup parameter set by said setting section;

said recognition section recognizing the object in the later frame acquired by said image pickup section.

5. An image processing method for an image processing apparatus which includes a recognition section adapted to recognize, based on a learning result obtained by learning of a learning image regarding a predetermined object, the object in a predetermined frame of an input image, and a setting section adapted to set a parameter to be used for a process to be carried out for a later frame which is later in time than the predetermined frame of the input image in response to a difference in image information between an object image, which is an image in a region of the object recognized in the predetermined frame, and the learning image, comprising:

recognizing, by the recognition section, based on the learning result obtained by learning of the learning image regarding the predetermined object, the object in the predetermined frame of the input image; and

setting a parameter to be used for a process to be carried out for a later frame which is later in time than the predetermined frame of the input image in response to a difference in image information between an object image, which is an image in a region of the object recognized in the predetermined frame, and the learning image;

the object in the later frame for which the process is carried out based on the parameter set by the setting step being recognized at the recognizing step.

6. A program for causing a computer to execute:

recognizing, based on a learning result obtained by learning of a learning image regarding a predetermined object, the object in the predetermined frame of the input image; and

setting a parameter to be used for a process to be carried out for a later frame which is later in time than the predetermined frame of the input image in response to a difference in image information between an object image, which is an image in a region of the object recognized in the predetermined frame, and the learning image;

the object in the later frame for which the process is carried out based on the parameter set by the setting step being recognized at the recognizing step.