Tracking a head of a subject

Patent metadata

Field	Value
Publication number	US-11100360-B2
Application number	US-201716467531-A
Country	US
Kind code	B2
Filing date	Dec 12, 2017
Priority date	Dec 14, 2016
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

An apparatus and method for tracking a head of a subject in a series of images includes receiving a series of images of at least a portion of a subject's head; tracking a position of the subject's head in the series of images based on positions of a first plurality of primary features of the subject's head; determining a first confidence level of the position of the subject's head based on the positions of the first plurality of primary features; monitoring a position of a secondary feature; and upon determining that the first confidence level is below a defined threshold, tracking the position of the subject's head based on the position of the secondary feature rather than the positions of the primary features.

First claim

The invention claimed is:

1. A method for tracking a head of a subject in a series of images, the method comprising acts of:
receiving a series of images of at least a portion of a subject's head;
tracking a position of the subject's head in the series of images based on positions of a first plurality of primary features of the subject's head;
determining a first confidence level of the position of the subject's head based on the positions of the first plurality of primary features;
monitoring a position of a secondary feature; and
upon determining that the first confidence level is below a defined threshold, tracking the position of the subject's head based on the position of the secondary feature rather than the positions of the first plurality of primary features,
wherein the secondary feature includes at least one feature specific to the head of the subject and not present in heads of all people.

2. The method according to claim 1 , wherein, for a particular image in the series of images, the first confidence level is based on a combination of confidence levels of the first plurality of primary features.

3. The method according to claim 1 , further comprising an act of:
during said tracking the position of the subject's head based on the positions of the first plurality of primary features, identifying a candidate secondary feature as a potential secondary feature to be used for tracking the subject's head.

4. The method according to claim 1 , wherein each primary feature comprises one of: a portion of an eye, a portion of a nose, a portion of a mouth, a portion of an eyebrow, and a portion of a chin.

5. The method according to claim 1 , wherein the secondary feature comprises a portion of an image of the received series of images.

6. The method according to claim 1 , wherein tracking the position of the subject's head based on the position of the secondary feature comprises applying at least one of a template matching technique and an image feature matching technique.

7. A processor configured to perform the method of claim 1 .

8. An apparatus for tracking a head of a subject, the system comprising:
an imager configured to receive a series of images representing at least a portion of a subject's head; and
a processing unit according to claim 7 .

9. The apparatus according to claim 8 , further comprising:
a camera for capturing the image data representing at least a portion of the subject's head.

10. The apparatus according to claim 8 , wherein the apparatus comprises one of a smart mirror, a tablet computer, a smartphone, a laptop computer and a desktop computer.

11. A method for tracking a head of a subject in a series of images, the method comprising acts of:
receiving a series of images of at least a portion of a subject's head;
tracking a position of the subject's head in the series of images based on positions of a first plurality of primary features of the subject's head;
determining a first confidence level of the position of the subject's head based on the positions of the first plurality of primary features;
monitoring a position of a secondary feature;
upon determining that the first confidence level is below a defined threshold, tracking the position of the subject's head based on the position of the secondary feature rather than the positions of the first plurality of primary features;
during said tracking the position of the subject's head based on the position of the secondary feature, monitoring positions of a second plurality of primary features of the subject's head;
determining a second confidence level of the position of the subject's head based on the positions of the second plurality of primary features; and
upon determining that the second confidence level is above a defined threshold, tracking a position of the subject's head based on the positions of the second plurality of primary features rather than the position of the secondary feature.

12. A method for tracking a head of a subject in a series of images, the method comprising acts of:
receiving a series of images of at least a portion of a subject's head;
tracking a position of the subject's head in the series of images based on positions of a first plurality of primary features of the subject's head;
determining a first confidence level of the position of the subject's head based on the positions of the first plurality of primary features;
monitoring a position of a secondary feature;
upon determining that the first confidence level is below a defined threshold, tracking the position of the subject's head based on the position of the secondary feature rather than the positions of the first plurality of primary features;
during said tracking the position of the subject's head based on the positions of the first plurality of primary features, identifying a candidate secondary feature as a potential secondary feature to be used for tracking the subject's head;
determining a confidence level of a position of the candidate secondary feature based on at least one of the positions of the first plurality of primary features; and
upon determining that the confidence level of the position of the candidate secondary feature is below a defined threshold, discarding the candidate secondary feature as a potential secondary feature to be used for tracking the subject's head.

13. A method for tracking a head of a subject in a series of images, the method comprising acts of:
receiving a series of images of at least a portion of a subject's head;
tracking a position of the subject's head in the series of images based on positions of a first plurality of primary features of the subject's head;
determining a first confidence level of the position of the subject's head based on the positions of the first plurality of primary features;
monitoring a position of a secondary feature;
upon determining that the first confidence level is below a defined threshold, tracking the position of the subject's head based on the position of the secondary feature rather than the positions of the first plurality of primary features;
during said tracking the position of the subject's head based on the positions of the first plurality of primary features, identifying a candidate secondary feature as a potential secondary feature to be used for tracking the subject's head;
fitting a three-dimensional model of the subject's head to coordinates representing the positions of the primary features;
updating the position of the three-dimensional model based on the first plurality of positions of the primary features obtained from a first image and a second, later image in the plurality of images; and
predicting a position of the candidate secondary feature in the three dimensional model based on the first plurality of positions of the primary features in the model.

14. The method according to claim 13 , further comprising acts of:
comparing the predicted position of the candidate secondary feature in the three dimensional model with a position of the candidate secondary feature determined from image feature tracking analysis of the first and second images; and
increasing a confidence level of the position of the candidate secondary feature if the predicted position is within a defined distance of the position determined from the image feature tracking analysis.

15. A non-transitory machine-readable medium comprising instructions which, when executed by a processor, cause the processor to:
track a position of a subject's head in a series of images based on positions of a first plurality of primary features of the subject's head;
de

Assignees

• Koninklijke Philips Nv

Inventors

• Van Bree Karl Catharina
• Velthoven Leo Jan

Classifications

• G06V10/768

  using context analysis, e.g. recognition aided by known co-occurring patterns · CPC title

• G06T7/246 Primary

  using feature-based methods, e.g. the tracking of corners or segments · CPC title

• G06V20/647

  by matching two-dimensional images to three-dimensional objects · CPC title

• G06V40/167

  using comparisons between temporally consecutive images · CPC title

• G06V40/165

  using facial parts and geometric relationships · CPC title