Information processing device, information processing method, and program

Patent metadata

Field	Value
Publication number	US-9418286-B2
Application number	US-201414525323-A
Country	US
Kind code	B2
Filing date	Oct 28, 2014
Priority date	Dec 19, 2013
Publication date	Aug 16, 2016
Grant date	Aug 16, 2016

Abstract

An information processing device includes a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit. The feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied.

First claim

What is claimed is:

1. An information processing device comprising:
a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and
a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit,
wherein the feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied,
wherein the feature amount extraction unit calculates the feature amount as an index value used to distinguish a first state in which a finger, which is the specific object, comes into contact with a board from a second state in which the finger does not come into contact with the board,
wherein based on the feature amount extracted by the feature amount extraction unit, the specific object recognition unit performs a process of determining whether the finger which is the specific object comes into contact with the board, and
wherein the feature amount extraction unit and the specific object recognition unit are each implemented via at least one processor.

2. The information processing device according to claim 1 , wherein the feature amount extraction unit performs the feature amount extraction process by setting the separated filter regions forming the separated filter in two images of the connected image.

3. The information processing device according to claim 1 , wherein the feature amount extraction unit extracts the feature amount by selectively applying filters determined to have high discrimination in first and second states of the specific object in a learning process performed in advance.

4. The information processing device according to claim 1 , further comprising:
a learning processing unit configured to perform a process of determining the filter with high discrimination by inputting a plurality of connected images indicating the first and second states of the specific object and extracting the feature amounts to which separated filters with different formats are applied.

5. The information processing device according to claim 1 , wherein the specific object recognition unit calculates a score by adding the feature amounts corresponding to the different separated filters and extracted by the feature amount extraction unit and performs the process of determining the position of the specific object based on the added score.

6. The information processing device according to claim 1 , wherein the specific object recognition unit calculates scores corresponding to pixels and obtained by adding the feature amounts corresponding to the pixels corresponding to the different separated filters and extracted by the feature amount extraction unit and performs the process of determining the position of the specific object based on a total score obtained by further adding the calculated scores corresponding to the pixels.

7. The information processing device according to claim 1 ,
wherein the feature amount extraction unit further extracts the feature amount as the index value used to determine whether the specific object is present in an image, and
wherein based on the feature amount extracted by the feature amount extraction unit, the specific object recognition unit performs a specific object detection process of determining whether the specific object is present or absent.

8. The information processing device according to claim 1 , wherein the separated filter is a filter in which filter regions with different luminance are set to be separated.

9. The information processing device according to claim 1 , wherein the feature amount extraction unit extracts the feature amount by setting the separated filter on an epipolar line corresponding to a feature point of one image of the connected image and the feature point on the other image of the connected image.

10. An information processing method performed in an information processing device, the method comprising:
extracting, by a feature amount extraction unit, a feature amount from a connected image generated by connecting images photographed from different viewpoints; and
performing, by a specific object recognition unit, a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit,
wherein the feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-fanned regions are set to be separated is applied,
wherein the feature amount extraction unit calculates the feature amount as an index value used to distinguish a first state in which a finger, which is the specific object, comes into contact with a board from a second state in which the finger does not come into contact with the board, and
wherein based on the feature amount extracted by the feature amount extraction unit, the specific object recognition unit performs a process of determining whether the finger which is the specific object comes into contact with the board.

11. A non-transitory computer-readable medium having embodied thereon a program, which when executed by a computer causes the computer to execute a method, the method comprising:
extracting a feature amount from a connected image generated by connecting images photographed from different viewpoints;
performing a process of determining a position of a specific object based on the extracted feature amount;
performing a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied;
calculating the feature amount as an index value used to distinguish a first state in which a finger, which is the specific object, comes into contact with a board from a second state in which the finger does not come into contact with the board; and
performing a process of determining whether the finger which is the specific object comes into contact with the board based on the extracted feature amount.

12. An information processing device comprising:
a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and
a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit,
wherein the feature amount extraction unit performs a feature amount extraction process to which a separated filter in which filter-formed regions are set to be separated is applied,
wherein the specific object recognition unit calculates a score by adding the feature amounts corresponding to the different separated filters and extracted by the feature amount extraction unit and performs the process of determining the position of the specific object based on the added score, and
wherein the feature amount extraction unit and the specific object recognition unit are each implemented via at least one processor.

13. An information processing device comprising:
a feature amount extraction unit configured to extract each feature amount from a connected image generated by connecting images photographed from different viewpoints; and
a specific object recognition unit configured to perform a process of determining a position of a specific object based on the feature amount extracted by the feature amount extraction unit,
wherein the feature amount extraction unit performs a feature amount e

Assignees

• Sony Corp

Inventors

• Yokono Jun

Classifications

• G06V10/7747 Primary

  Organisation of the process, e.g. bagging or boosting · CPC title

• G06F2218/02

  Preprocessing · CPC title

• G06F2218/08

  Feature extraction · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06F18/2148

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title