Information processing apparatus, three-dimensional position calculation method, and program

Patent metadata

Field	Value
Publication number	US-9317924-B2
Application number	US-201113169662-A
Country	US
Kind code	B2
Filing date	Jun 27, 2011
Priority date	Jun 30, 2010
Publication date	Apr 19, 2016
Grant date	Apr 19, 2016

Abstract

An information processing apparatus includes a region segmentation unit configured to segment each of a plurality of images shot by an imaging apparatus for shooting an object from a plurality of viewpoints, into a plurality of regions based on colors of the object, an attribute determination unit configured to determine, based on regions in proximity to intersections between scanning lines set on the each image and boundary lines of the regions segmented by the region segmentation unit in the each image, attributes of the intersections, a correspondence processing unit configured to obtain corresponding points between the images based on the determined intersections' attributes, and a three-dimensional position calculation unit configured to calculate a three-dimensional position of the object based on the obtained corresponding points.

First claim

What is claimed is:

1. An apparatus comprising a memory and at least one processor that executes a program to function as:
a region extraction unit configured to extract a first region having predetermined color information from a first image sensed by an imaging apparatus in a first viewpoint and a second region having the predetermined color information from a second image sensed by an imaging apparatus in a second viewpoint different from the first viewpoint;
a first determination unit configured to determine whether a first area of the extracted first region in the first image is larger than a first threshold value, and determine whether a second area of the extracted second region in the second image is larger than a second threshold value;
an obtaining unit configured to obtain first intersection points where a first line set in the first image intersects first pixels of an outline of the first region, and the first determination unit determines that the first area of which in the first image is larger than the first threshold value, and obtain second intersection points where a second line set in the second image intersects second pixels of an outline of the second region, and the first determination unit determines that the second area of which in the second image is larger than the second threshold value;
an attribute determination unit configured to determine first attributes which indicate whether the first pixels at the obtained first intersection points are on a right side or on a left side of the first region in the first image, and determine second attributes which indicate whether the second pixels at the obtained second intersection points are on a right side or on a left side of the second region in the second image;
a second determination unit configured to determine whether the first attributes of the first intersection points on the first line set in the first image match with second attributes of the second intersection points on the second line set in the second image;
a correspondence processing unit configured to obtain corresponding points between the first image and the second image based on a result of the second determination unit; and
a calculation unit configured to calculate at least a depth value of an object based on obtained corresponding points.

2. The apparatus according to claim 1 , further comprising:
a line setting unit configured to set lines on each image.

3. The apparatus according to claim 1 , wherein the imaging apparatus comprises two imaging apparatuses attached to a head-mounted display or handheld display.

4. The apparatus according to claim 2 , wherein the imaging apparatus comprises two imaging apparatuses located so as to provide parallelly aligned optical-axis directions and the same viewpoint heights, and
wherein the line setting unit sets lines as a plurality of line segments arranged in each image of the object shot by the two imaging apparatuses, in parallel with a line segment connecting the two imaging apparatuses.

5. The apparatus according to claim 2 , wherein the lines are epipolar lines.

6. The apparatus according to claim 2 , further comprising:
a scanning line position control unit configured to control positions of the lines set by the line setting unit according to the regions extracted by the region extraction unit in each image.

7. The apparatus according to claim 1 , further comprising:
a generation unit configured to generate a first set of the first attributes of the first intersection points in the first line in the first image and generate a second set of the second attributes of the second intersection points in the second line in the second image,
wherein the second determination unit is configured to determine whether the first set of the first attributes of the first intersection points in the first line in the first image matches with the second set of the second attributes of the second intersection points in the second line in the second image.

8. The apparatus according to claim 7 , wherein the correspondence processing unit calculates a degree of coincidence of the first set of the first attributes and the second set of the second attributes generated by the generation unit for each line, and obtains corresponding points between the first image and the second image based on the calculated degree of coincidence.

9. The apparatus according to claim 8 , wherein the correspondence processing unit obtains, out of intersections not determined to be corresponding points based on calculated degree of coincidence, other intersections on the lines passing the intersections determined to be corresponding points based on the calculated degree of coincidence, as a corresponding point.

10. A method performed by an information processing apparatus, the method comprising:
extracting a first region having predetermined color information from a first image sensed by an imaging apparatus in a first viewpoint and a second region having the predetermined color information from a second image sensed by an imaging apparatus in a second viewpoint different from the first viewpoint;
first determining to determine whether a first area of the extracted first region in the first image is larger than a first threshold value, and determine whether a second area of the extracted second region in the second image is larger than a second threshold value;
obtaining first intersection points where a first line set in the first image intersects first pixels of an outline of the first region, and the first determining determines that the first area of which in the first image is larger than the first threshold value, and obtaining second intersection points where a second line set in the second image intersect second pixels of an outline of the second region, and the first determining determines that the second area of which in the second image is larger than the second threshold value;
attribute determining to determine first attributes which indicate whether the first pixels at the obtained first intersection points are on a right side or on a left side of the first region in the first image, and determine second attributes which indicate whether the second pixels at the obtained second intersection points are on a right side or on a left side of the second region in the second image;
second determining to determine whether first attributes of the first intersection points on the first line set in the first image match with second attributes of the second intersection points on the second line set in the second image;
obtaining corresponding points between the first image and the second image based on a result of the second determining; and
calculating at least a depth value of an object based on the obtained corresponding points.

11. A non-transitory computer-readable storage medium storing a program for causing a computer to execute a method comprising:
extracting a first region having predetermined color information from a first image sensed by an imaging apparatus in a first viewpoint and a second region having the predetermined color information from a second image sensed by an imaging apparatus in a second viewpoint different from the first viewpoint;
first determining whether an area of the extracted first region in the first image and the second image is larger than a first threshold value, and determining whether an area of the extracted second region in the second image is larger than a second threshold value;
obtaining first intersection points where a first line set in the first image intersects first pixels of outline of the first region, and the first determining determines that the first area of which in the first image

Assignees

• Aratani Shinichi
• Takemoto Kazuki
• Aso Takashi
• Canon Kk

Inventors

• Aratani Shinichi
• Takemoto Kazuki
• Aso Takashi

Classifications

• H04N2013/0074

  Stereoscopic image analysis · CPC title

• G06T7/0065

  Physics · mapped topic

• G06T2207/10012

  Stereo images · CPC title

• G06T2207/10021

  Stereoscopic video; Stereoscopic image sequence · CPC title

• G06T7/0075 Primary

  Physics · mapped topic