Three-dimensional coordinate computing apparatus, three-dimensional coordinate computing method, and non-transitory computer readable recording medium having therein program for three-dimensional coordinate computing

Patent metadata

Field	Value
Publication number	US-9892516-B2
Application number	US-201514845493-A
Country	US
Kind code	B2
Filing date	Sep 4, 2015
Priority date	Sep 26, 2014
Publication date	Feb 13, 2018
Grant date	Feb 13, 2018

Abstract

A three-dimensional coordinate computing apparatus includes an image selecting unit and a coordinate computing unit. The image selecting unit selects a first selected image from multiple captured images, and selects a second selected image from multiple subsequent images captured by the camera after the first selected image has been captured. The second selected image is selected based on a distance between a position of capture of the first selected image and a position of capture of each of the multiple subsequent images and the number of corresponding feature points, each of which corresponds to one of feature points extracted from the first selected image and one of feature points extracted from each of the multiple subsequent images. The coordinate computing unit computes three-dimensional coordinates of the multiple corresponding feature points based on two-dimensional coordinates of each corresponding feature point in the first and second selected images.

First claim

What is claimed is:

1. A three-dimensional coordinate computing apparatus comprising:
a memory;
at least one processor, coupled to the memory, configured to cause the following to be performed:
selecting a first selected image from multiple captured images, the multiple captured images being captured by a camera, the first selected image including feature points;
determining a position of capture of the first selected image based on a position of a marker in the first selected image;
determining a position of capture of each of multiple subsequent images based on a position of the marker in each of the multiple subsequent images, the multiple subsequent images being captured by the camera after the first selected image has been captured and the multiple subsequent images each including feature points;
determining distances between the position of capture of the first selected image and the position of capture of each of the multiple subsequent images;
determining a number of corresponding feature points between the feature points extracted from the first selected image and the feature points extracted from each of the multiple subsequent images;
selecting a second selected image from the multiple subsequent images based on the determined distance of the second selected image and when the determined number of corresponding feature points of the second selected image are greater than a predetermined threshold; and
outputting three-dimensional coordinates of the corresponding feature points based on two-dimensional coordinates of each corresponding feature point in each of the first selected image and the second selected image;
registering the outputted three-dimensional coordinates on a feature point map;
displaying superimposed image information based on the feature point map,
wherein when selecting one subsequent image among the multiple subsequent images as the second selected image, the processor is further configured to cause the following to be performed:
determining a camera-marker distance corresponding to a distance between the position of capture of the one subsequent image and the marker based on the position of the marker in the first selected image and the position of the marker of the one subsequent image,
determining a distance threshold based on the camera-marker distance and an initial value of a reference inter-camera distance, and
determining whether to select the one subsequent image as the second selected image based on a result of comparison between the distance between positions of capture that is computed for the one subsequent image and the distance threshold.

2. The three-dimensional coordinate computing apparatus according to claim 1 ,
wherein the distance threshold is determined further based on an optimum value of an amount of movement of a pixel and a focal length of the camera.

3. The three-dimensional coordinate computing apparatus according to claim 1 ,
wherein the processor is further configured to cause the following to be performed:
determining an evaluation value that evaluates whether an operation in which a position of the camera is not changed from the capture of the first selected image until the capture of each of the multiple subsequent images,
rotating the camera around a direction of capture, based on the position of the marker in the first selected image and the position of the marker of each of the multiple subsequent images,
determining, when the evaluation value is greater than a predetermined threshold, that a subsequent image that corresponds to the evaluation value among the multiple subsequent images is not selected as the second selected image, and
outputting notification information that notifies a user so as to move the position of capture.

4. The three-dimensional coordinate computing apparatus according to claim 1 ,
wherein the processor is further configured to cause the following to be performed: determining whether to select a second captured image as the first selected image, based on an amount of movement from a position of capture of a first captured image among the multiple captured images to a position of capture of the second captured image among the multiple captured images.

5. The three-dimensional coordinate computing apparatus according to claim 1 ,
wherein the processor is further configured to cause the following to be performed:
determining whether to select a second captured image as the first selected image, based on an amount of deviation between the position of the marker in a first captured image among the multiple captured images and the position of the marker in the second captured image among the multiple captured images.

6. The three-dimensional coordinate computing apparatus according to claim 1 ,
wherein the processor is further configured to cause the following to be performed:
determining whether to select the one captured image as the first selected image, based on an area of the marker in one captured image among the multiple captured images.

7. A three-dimensional coordinate computing method comprising:
selecting, by a computer, a first selected image from multiple captured images, the multiple captured images being captured by a camera, the first selected image including feature points; determining a position of capture of the first selected image based on a position of a marker in the first selected image;
determining a position of capture of each of multiple subsequent images based on a position of the marker in each of the multiple subsequent images, the multiple subsequent images being captured by the camera after the first selected image has been captured and the multiple subsequent images each including feature points;
determining distances between the position of capture of the first selected image and the position of capture of each of the multiple subsequent images;
determining a number of corresponding feature points between the feature points extracted from the first selected image and the feature points extracted from each of the multiple subsequent images;
selecting a second selected image from the multiple subsequent images based on the determined distance of the second selected image and when the determined number of corresponding feature points of the second selected image are greater than a predetermined threshold; and
outputting three-dimensional coordinates of the corresponding feature points based on two-dimensional coordinates of each corresponding feature point in each of the first selected image and the second selected image;
registering the outputted three-dimensional coordinates on a feature point map;
displaying superimposed image information based on the feature point map,
wherein when selecting one subsequent image among the multiple subsequent images as the second selected image, the processor is further configured to cause the following to be performed:
determining a camera-marker distance corresponding to a distance between the position of capture of the one subsequent image and the marker based on the position of the marker in the first selected image and the position of the marker of the one subsequent image,
determining a distance threshold based on the camera-marker distance and an initial value of a reference inter-camera distance, and
determining whether to select the one subsequent image as the second selected image based on a result of comparison between the distance between positions of capture that is computed for the one subsequent image and the distance threshold.

8. The three-dimensional coordinate computing method according to claim 7 , wherein
the distance threshold is determined further based on an optimum value of an amount of movement of a pixel and a focal length of the ca

Assignees

• Fujitsu Ltd

Inventors

• Moteki Atsunori
• Yamaguchi Nobuyasu
• Matsuda Takahiro

Classifications

• G06T7/73 Primary

  using feature-based methods · CPC title

• G06T7/593 Primary

  from stereo images · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T7/579

  from motion · CPC title

• G06T2207/30208

  Marker matrix · CPC title