Position detection device, position detection method, and storage medium

Patent metadata

Field	Value
Publication number	US-10212324-B2
Application number	US-201615363248-A
Country	US
Kind code	B2
Filing date	Nov 29, 2016
Priority date	Dec 1, 2015
Publication date	Feb 19, 2019
Grant date	Feb 19, 2019

Abstract

An image processing device includes a detection unit configured to detect an object from an image captured by each of a plurality of image capturing devices, a determination unit configured to determine whether the object is detected by two image capturing devices or more in the image capturing devices, a first estimation unit configured to estimate, when the object have been detected by the two image capturing devices or more, a three-dimensional position and information on a height of the object based on a detected position where the object is detected in an image captured for each of the two image capturing devices and positions and orientations of the two image capturing devices, and a second estimation unit configured to estimate, when the object have been detected by a single image capturing device, the three-dimensional position of the object.

First claim

What is claimed is:

1. An image processing device comprising:
one or more processors; and
one or more memories coupled to the one or more processors, the memories having stored thereon instructions which, when executed by the one or more processors, cause the device to:
detect an object from an image captured by each of a plurality of image capturing devices;
determine whether an object of interest is detected by at least two image capturing devices or a single image capturing device in the image capturing devices;
estimate, when the object of interest is detected by the at least two image capturing devices, a three-dimensional position and information on a height of the object based on a detected position where the object of interest is detected in an image captured by each of the at least two image capturing devices and positions and orientations of the at least two image capturing devices; and
estimate, when the object of interest is detected by the single image capturing device in the image capturing devices, the three-dimensional position of the object of interest based on a detected position where the object of interest is detected in an image captured by the single image capturing device, a position and an orientation of the single image capturing device, and the estimated information on the height.

2. The image processing device according to claim 1 , when executed by the one or more processors, further cause the device to: identify, when the object of interest is detected by the single image capturing device, information on a height of the object detected by the single image capturing device, from the estimated information on the height,
use the information, on the identified height of the object.

3. The image processing device according to claim 2 , when executed by the one or more processors, further cause the device to:
track an object detected from the image captured by each of the image capturing devices; and
identify the information on the height of the object detected by the single image capturing device, from the estimated information on the height, based on a tracking result.

4. The image processing device according to claim 2 , when executed by the one or more processors, further cause the device to: extract respective features from detected objects; and
identify the information on the height of the object detected by the single image capturing device, from the estimated information on the height, by comparing the extracted respective features.

5. The image processing device according to claim 2 , when executed by the one or more processors, further cause the device to: use, when the information on the height of the object detected by the single image capturing device is not identified, information on a height set in advance.

6. The image processing device according to claim 1 , when executed by the one or more processors, further cause the device to: determine whether the object of interest is detected by at least two image capturing devices in the plurality of image capturing devices, by determining whether the object detected by one of the plurality of image capturing devices is detected by another one of the plurality of image capturing devices based on the positions and the orientations of the image capturing devices.

7. The image processing device according to claim 6 , when executed by the one or more processors, further cause the device to: store area information, and determine whether the object of interest is detected by at least two image capturing devices in the plurality of image capturing devices, by referring to the area information, whether the object detected by one of the plurality of image capturing devices is detected by another one of the plurality of image capturing devices, the area information representing an area where an image captured by the one of the plurality of image capturing devices overlaps with an image captured by the another one of the plurality of image capturing devices based on the positions and the orientations of the image capturing devices.

8. An image processing method comprising:
detecting an object from an image captured by each of a plurality of image capturing devices;
determining whether an object of interest is detected by at least two image capturing devices or a single image capturing device in the image capturing devices;
estimating, when the object of interest is detected by the at least two image capturing devices, a three-dimensional position and information on a height of the object based on a detected position where the object of interest is detected in an image captured by each of the at least two image capturing devices and positions and orientations of the at least two image capturing devices; and
estimating, when the object of interest is detected by the single image capturing device in the image capturing devices, the three-dimensional position of the object of interest based on a detected position where the object of interest is detected in an image captured by the single image capturing device, a position and an orientation of the single image capturing device, and the estimated information on the height.

9. The image processing method according to claim 8 , further comprising identifying, when the object of interest is determined to have been detected by the single image capturing device, information on a height of the object detected by the single image capturing device, from the information on the estimated height,
wherein the estimating uses the identified information on the height of the object.

10. The image processing method according to claim 9 , further comprising tracking an object detected from the image captured by each of the image capturing devices,
wherein the identifying identifies the information on the height of the object detected by the single image capturing device, from the information on the estimated height, based on a tracking result obtained by the tracking.

11. The image processing method according to claim 9 , further comprising extracting respective features from objects detected by the detecting,
wherein the identifying identifies the information on the height of the object detected by the single image capturing device, from the information on the height estimated by the estimating, by comparing the extracted respective features.

12. The image processing method according to claim 9 , wherein the estimating uses, when the identifying does not identify the information on the height of the object detected by the single image capturing device, information on a height set in advance.

13. The image processing method according to claim 8 , wherein the determining determines whether the object of interest is detected by at least two image capturing devices in the plurality of image capturing devices, by determining whether the object detected by one of the plurality of image capturing devices is detected by another one of the plurality of image capturing devices based on the positions and the orientations of the image capturing devices.

14. A non-transitory storage medium storing therein a program causing a computer to perform a method comprising:
detecting an object from an image captured by each of a plurality of image capturing devices;
determining whether an object of interest is detected by at least two image capturing devices or a single image capturing device in the image capturing devices;
first estimating, when the object of interest is detected by the at least two image capturing devices, a three-dimensional position and information on a height of the object based on a detected position where the object of in

Assignees

• Canon Kk

Inventors

• Uchiyama Hiroyuki
• Yano Kotaro
• Umeda Ichiro
• Guo Muling

Classifications

• G06T2207/30196

  Human being; Person · CPC title

• G06T7/62

  of area, perimeter, diameter or volume · CPC title

• G06T7/292

  Multi-camera tracking · CPC title

• G01S3/00

  Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic or electromagnetic waves, or particle emission, not having a directional significance, are being received (position-fixing by co-ordinating a plurality of determinations of direction or position lines G01S5/00) · CPC title

• G03B35/08

  by simultaneous recording · CPC title