IP Library Granted Patent US 10,089,726
Granted Patent B2
US 10,089,726 · App. 15/051,462 · Granted Oct 2, 2018

Image processing apparatus, image processing method, and storage medium, relating to generating an image corresponding to a predetermined three-dimensional shape by transforming a captured image

Inventor: Kazunari Iwamoto (Kawasaki, JP)
Assignee: Canon Kabushiki Kaisha
G06T5/006G06T3/005
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,089,726
App. No.
15/051,462
Granted
Oct 2, 2018
Kind
B2
Abstract

An image processing apparatus includes an acquisition unit configured to acquire information for identifying a position of a plane in a captured image, where the captured image includes a structure composed of a plurality of planes as an object, a determination unit configured to determine a correspondence relationship between a region corresponding to the plane in the captured image and a region in an overhead image to be created, according to the information acquired by the acquisition unit, and a generation unit configured to correct an image of the region corresponding to the plane in the captured image so that the corrected image corresponds to the region in the overhead image to be created, according to the correspondence relationship determined by the determination unit, and generate an overhead image composed of a plurality of corrected images that are combined with each other.

Claims (28)

1. An image processing apparatus comprising:

one or more processors; and

one or more memories storing instructions that, when executed by the one or more processors, cause the image processing apparatus to perform operations comprising:

acquiring information for identifying a position of a vertex of a plane in a captured image, the captured image including a structure composed of a plurality of planes as an object;

identifying points corresponding to positions of vertexes of the plane on a spherical coordinate that corresponds to an image-capturing range of an image-capturing unit that captures the captured image based on the information acquired by the acquiring;

correcting positions of the points on the spherical coordinate to form a three-dimensional shape having the points on the spherical coordinate as the vertexes, into a predetermined three-dimensional shape; and

generating an overhead image by making a region in the captured image corresponding to the positions of the points corrected by the correcting, as a region corresponding to the plane.

2. The image processing apparatus according to claim 1 , wherein the correcting corrects the positions of the points on the spherical coordinate to form the three-dimensional shape having the points on the spherical coordinate as the vertexes into a rectangular parallelepiped.

3. The image processing apparatus according to claim 1 , wherein the operations further comprise:

storing information of a plurality of three-dimensional shapes, and

selecting a predetermined three-dimensional shape from the plurality of the three-dimensional shapes.

4. The image processing apparatus according to claim 3 , wherein the selecting selects the predetermined three-dimensional shape based on a number of points corresponding to the positions of the vertexes of the plane.

5. The image processing apparatus according to claim 1 , wherein the generating corrects images of regions corresponding to a plurality of planes in the captured image so that the images correspond to the planes of the predetermined three-dimensional shape formed by connecting the plurality of the points corrected by the correcting.

6. The image processing apparatus according to claim 1 , wherein the acquiring acquires a position specified by a user with respect to the captured image as the information for identifying a position of the plane.

7. The image processing apparatus according to claim 1 , wherein the acquiring detects an object having a predetermined color or pattern from the captured image and acquires a position of the object having the predetermined color or pattern as the information for identifying a position of the plane.

8. The image processing apparatus according to claim 1 , wherein the generating generates the overhead image on which an image representing a position of the image-capturing unit for capturing the captured image is superimposed.

9. The image processing apparatus according to claim 1 , wherein the generating generates the overhead image on which an image representing an image-capturing direction of the image-capturing unit for capturing the captured image is superimposed.

10. The image processing apparatus according to claim 1 , wherein the operations further comprise transmitting the overhead image generated by the generating to the image-capturing unit for capturing the captured image, via a network.

11. An image processing method comprising:

acquiring information for identifying a position of a vertex of a plane in a captured image, the captured image including a structure composed of a plurality of planes as an object;

identifying points corresponding to positions of vertexes of the plane on a spherical coordinate that corresponds to an image-capturing range of an image-capturing unit that captures the captured image based on the information acquired by the acquiring,

correcting positions of the points on the spherical coordinate to form a three-dimensional shape having the points on the spherical coordinate as the vertexes, into a predetermined three-dimensional shape; and

generating an overhead image by making a region in the captured image corresponding to the positions of the points corrected by the correcting, as a region corresponding to the plane.

12. A non-transitory computer readable storage medium storing a program that, when executed, causes a computer to perform a process comprising:

acquiring information for identifying a position of a vertex of a plane in a captured image, the captured image including a structure composed of a plurality of planes as an object;

identifying points corresponding to positions of vertexes of the plane on a spherical coordinate that corresponds to an image-capturing range of an image-capturing unit that captures the captured image based on the information acquired by the acquiring,

correcting positions of the points on the spherical coordinate to form a three-dimensional shape having the points on the spherical coordinate as the vertexes, into a predetermined three-dimensional shape; and

generating an overhead image by making a region in the captured image corresponding to the positions of the points corrected by the correcting, as a region corresponding to the plane.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 6, 2016
From: IWAMOTO, KAZUNARI
To: CANON KABUSHIKI KAISHA
Reel/Frame 038629/0452 →
Priority Claims (1)
JP 2015-037436 · Feb 26, 2015 · national
Continuity (1)
Related Publication 20160253780A1 · Sep 1, 2016