ESTIMATION SYSTEM, ESTIMATION METHOD, AND ESTIMATION PROGRAM

• US 20180182124A1
• Filed: 12/27/2017
• Published: 06/28/2018
• Est. Priority Date: 12/27/2016
• Status: Abandoned Application

• Current Assignee: FOVE, inc.
• Original Assignee: FOVE, inc.
• Inventors: Savkin, Pavel
• Application Number:
  US15/855,126
• Publication Number:
  US 20180182124A1
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

To specify a position and a direction of a target having marks within a predetermined space from captured image.

There is provided an estimation system for estimating a position and a posture of a fitting harness, which includes a plurality of marks, which a user wears, and in which the user watches a video image, within a predetermined space. The estimation system stores preset posture data of a case in which the fitting harness is present in each of a plurality of regions different from each other included in the predetermined space, for each of the regions; receives a captured image of the predetermined space in which the fitting harness is included; receives posture information indicating the posture of the fitting harness from the fitting harness; and estimates a region having a possibility that the fitting harness is present among the plurality of regions using the captured image and the preset posture data, and estimates the region by narrowing the preset posture data to be used for a second captured image from the position and the posture in a first captured image based on posture information received after the first captured image is received, when the position and the posture of the fitting harness are estimated based on the second captured image following the first captured image among the sequentially transmitted captured images.

Claims

1. An estimation system comprising:

a fitting harness which a user wears and in which the user watches a video image;

an estimation device which estimates a position and a posture of the fitting harness within a predetermined space; and

an image capturing unit which captures an image of the predetermined space,

wherein the fitting harness includes

a plurality of marks which are provided on an external surface,

a detection unit which sequentially detects posture information indicating the posture of the fitting harness, and

a first transmission unit which sequentially transmits the posture information to the estimation device, and

wherein the estimation device includes

a storage unit which stores preset posture data of a case in which the fitting harness is present in each of a plurality of regions different from each other included in the predetermined space, for each of the regions,

a first reception unit which receives the posture information,

a second reception unit which receives a captured image from the image capturing unit, and

an estimation unit which estimates a region having a possibility that the fitting harness is present among the plurality of regions using the captured image and the preset posture data, and estimates the region by narrowing the preset posture data to be used for a second captured image from the position and the posture in a first captured image based on posture information received after the first captured image is received, when the position and the posture of the fitting harness are estimated based on the second captured image following the first captured image among the sequentially transmitted captured images.

2. The estimation system according to claim 1,

wherein a unique identifier is allocated to each of the plurality of marks, and

wherein the estimation unit estimates a position and a posture of the fitting harness by estimating which one of the unique identifiers corresponds to the mark of the fitting harness included in the captured image.

3. The estimation system according to claim 1 or 2,

wherein the posture information includes information indicating directions from a basic position with respect to three axes, and information indicating a state of rotation with respect to each of the axes.

4. The estimation system according to claim 1,

wherein the estimation unit further specifies a direction of a normal vector set for each of the marks and estimates the position and the posture of the fitting harness based on the specified normal vector.

5. The estimation system according to claim 1,

wherein the plurality of marks are LEDs.

6. The estimation system according to claim 1, further comprising:

a video image transmission device which generates a video image to be displayed in the fitting harness, based on the position and the posture of the fitting harness in the predetermined space estimated by the estimation unit, and transmits the video image.

7. The estimation system according to claim 1,

wherein the storage unit further stores a plurality of pieces of received posture information, and

wherein the estimation unit performs estimation using the posture information stored in the storage unit when estimation of the region is unable to be executed.

8. The estimation system according to claim 1,

wherein the preset posture data is information in which information for specifying a range included in the predetermined space, and information for calculating presence probability for determining whether or not the fitting harness is included in the range are mapped to each other.

9. An estimation method of estimating a position and a posture of a fitting harness, which includes a plurality of marks, which a user wears, and in which the user watches a video image, within a predetermined space, the estimation method comprising:

a storing step of storing preset posture data of a case in which the fitting harness is present in each of a plurality of regions different from each other included in the predetermined space, for each of the regions;

a first receiving step of receiving a captured image of the predetermined space in which the fitting harness is included;

a second receiving step of receiving posture information indicating the posture of the fitting harness from the fitting harness; and

an estimating step of estimating a region having a possibility that the fitting harness is present among the plurality of regions using the captured image and the preset posture data, and estimating the region by narrowing the preset posture data to be used for a second captured image from the position and the posture in a first captured image based on posture information received after the first captured image is received, when the position and the posture of the fitting harness are estimated based on the second captured image following the first captured image among the sequentially transmitted captured images.

10. An estimation program for causing a computer to estimate a position and a posture of a fitting harness, which includes a plurality of marks, which a user wears, and in which the user watches a video image, within a predetermined space, the estimation program realizing:

a storing function of storing preset posture data of a case in which the fitting harness is present in each of a plurality of regions different from each other included in the predetermined space, for each of the regions;

a first receiving function of receiving a captured image of the predetermined space in which the fitting harness is included;

a second receiving function of receiving posture information indicating the posture of the fitting harness from the fitting harness; and

an estimating function of estimating a region having a possibility that the fitting harness is present among the plurality of regions using the captured image and the preset posture data, and estimating the region by narrowing the preset posture data to be used for a second captured image from the position and the posture in a first captured image based on posture information received after the first captured image is received, when the position and the posture of the fitting harness are estimated based on the second captured image following the first captured image among the sequentially transmitted captured images.