Systems and Methods for Estimating a Three-Dimensional Pose

Patent metadata

Field	Value
Publication number	US-2019200902-A1
Application number	US-201816220117-A
Country	US
Kind code	A1
Filing date	Dec 14, 2018
Priority date	Dec 28, 2017
Publication date	Jul 4, 2019
Grant date	—

Abstract

A method for estimating a pose of an oral hygiene device including a pattern and a plurality of groups of visual markers relative to a location includes (i) receiving image data reproducible as an image of at least a portion of the oral hygiene device; (ii) analyzing the image data to identify a region of interest within the image; (iii) identifying, using at least one of the one or more processors, all candidate visual markers within the region of interest; (iv) obtaining a first proposed three-dimensional pose of the oral hygiene device; (v) validating the first proposed three-dimensional pose of the oral hygiene device; and (vi) obtaining a second proposed three-dimensional pose of the oral hygiene device based on the validated first proposed three-dimensional pose.

First claim

What is claimed is:

1 . A method for estimating a pose of an oral hygiene device relative to a location, the oral hygiene device including a pattern and a plurality of groups of visual markers, the method comprising:
receiving image data reproducible as an image of at least a portion of the oral hygiene device; analyzing, using one or more processors, the image data to identify a region of interest within the image, the region of interest including at least a portion of the pattern therein; identifying, using at least one of the one or more processors, all candidate visual markers from the plurality of groups of visual markers within the region of interest; obtaining a first proposed three-dimensional pose of the oral hygiene device; validating the first proposed three-dimensional pose of the oral hygiene device; and obtaining a second proposed three-dimensional pose of the oral hygiene device based on the validated first proposed three-dimensional pose.

2 . The method of claim 1 , wherein responsive to identifying the region of interest, segmenting, using at least one of the one or more processors, the region of interest into a plurality of sub-regions, each of the plurality of sub-regions being defined by a plurality of pixels having a common color.

3 . The method of claim 1 , wherein the obtaining the first proposed three-dimensional pose of the oral hygiene device includes:
creating a plurality of distinct sets of the candidate visual markers; selecting a first one of the plurality of distinct sets of the candidate visual markers; selecting a first one of a plurality of distinct sets of model markers associated with a three-dimensional model of the oral hygiene device; and evaluating a set of the candidate visual markers and a set of model markers using a perspective-three-point algorithm to obtain the proposed three-dimensional pose of the oral hygiene device.

4 . The method of claim 1 , wherein the validating the first proposed three-dimensional pose includes:
based on the proposed three-dimensional pose of the oral hygiene device, predicting a position within the region of interest for a predetermined number of the candidate visual markers; and comparing the predicted positions for the predetermined number of the candidate visual markers with actual positions of all of the candidate visual markers within the region of interest; and determining that at least a substantial portion of the predicted positions correspond with the actual positions.

5 . The method of claim 1 , wherein the analyzing the image data includes using one or more filters, the one or more filters including a movement filter, a color filter, a shape filter, or any combination thereof.

6 . The method of claim 1 , wherein the identifying all candidate visual markers is based on a shape and a color of each of the plurality of sub-regions.

7 . The method of claim 1 , wherein each of the plurality of distinct sets of the candidate visual markers includes at least four candidate visual markers and each of the plurality of distinct sets of the model markers includes at least four model markers.

8 . The method of claim 1 , further comprising:
receiving a second set of image data reproducible as a second image of at least a portion of the oral hygiene device; identifying a second region of interest within the second image based on the validated three-dimensional pose of the oral hygiene device.

9 . The method of claim 1 , further comprising:
adjusting, based on the validated three-dimensional pose of the oral hygiene device, a threshold for segmenting the second region of interest to aid in identifying pixels having different colors in the second region of interest.

10 . A method for estimating a pose of an oral hygiene device relative to a location, the oral hygiene device including a pattern and a plurality of groups of visual markers, the method comprising:
(a) receiving image data reproducible as an image of at least a portion of the oral hygiene device; (b) analyzing, using one or more processors, the image data to identify a region of interest within the image, the region of interest including at least a portion of the pattern therein; (c) responsive to identifying the region of interest, segmenting, using at least one of the one or more processors, the region of interest into a plurality of sub-regions, each of the plurality of sub-regions being defined by a plurality of pixels having a common color; (d) identifying, using at least one of the one or more processors, all candidate visual markers from the plurality of groups of visual markers within the region of interest; (e) creating a plurality of distinct sets of the candidate visual markers; (f) selecting a first one of the plurality of distinct sets of the candidate visual markers; (g) selecting a first one of a plurality of distinct sets of model markers associated with a three-dimensional model of the oral hygiene device; (h) evaluating the selected set of the candidate visual markers and the selected set of model markers using a perspective-three-point algorithm to obtain a proposed three-dimensional pose of the oral hygiene device; (i) based on the proposed three-dimensional pose of the oral hygiene device, predicting a position within the region of interest for a predetermined number of the candidate visual markers; (j) comparing the predicted positions for the predetermined number of the candidate visual markers with actual positions of all of the candidate visual markers within the region of interest; (k) responsive to a determination that at least a substantial portion of the predicted positions correspond with the actual positions, validating the proposed three-dimensional pose; and (l) responsive to a determination that less than the substantial portion of the predicted positions correspond with the actual positions, repeating steps (f)-(k).

11 . The method of claim 10 , further including responsive to the proposed three-dimensional pose being validated, comparing all of the candidate visual markers and all of the model markers using an algorithm to obtain a second proposed three-dimensional pose of the oral hygiene device.

12 . The method of claim 10 , wherein the analyzing the first image data includes using one or more filters, the one or more filters including a movement filter, a color filter, a shape filter, or any combination thereof.

13 . The method of claim 10 , wherein the identifying all candidate visual markers is based on a shape and a color of each of the plurality of sub-regions.

14 . The method of claim 10 , wherein each of the plurality of distinct sets of the candidate visual markers includes at least four candidate visual markers and each of the plurality of distinct sets of the model markers includes at least four model markers.

15 . The method of claim 10 , further comprising:
receiving a second set of image data reproducible as a second image of at least a portion of the oral hygiene device; identifying a second region of interest within the second image based on the validated three-dimensional pose of the oral hygiene device.

16 . The method of claim 15 , further comprising:
adjusting, based on the validated three-dimensional pose of the oral hygiene device, a threshold for segmenting the second region of interest to aid in identifying pixels having different colors in the second region of interest.

17 . A motion tracking system comprising:
an oral hygiene device including a head and a handle; a tracking element coupled to the oral hygiene dev

Assignees

• Colgate Palmolive Co

Inventors

• El Kouby-Benichou Vincent
• Giroud Oliver
• Serval Thomas
• Nicolas Yann

Classifications

• A61B5/1127 Primary

  using markers · CPC title

• A46B15/0002 Primary

  Arrangements for enhancing monitoring or controlling the brushing process · CPC title

• G06F18/256

  of results relating to different input data, e.g. multimodal recognition · CPC title

• A61B5/1128

  using image analysis (A61B5/1127 takes precedence) · CPC title

• G06T2207/30036

  Dental; Teeth · CPC title