Systems and methods to estimate human length
Systems and methods use a three-dimensional snapshot of an infant, child, adolescent, or adult where the subject may have bent legs and an unaligned head position, to provide an estimate of human length. The system identifies anatomical features from the digital information and generates a virtual skeleton. The cumulative distances between pseudo-joints of the virtual skeleton provide an estimate of human length. Comparing length estimates from multiple three-dimensional snapshots of the same individual acquired over time provide an indication of growth of the infant, child, or adolescent. Daily estimates of length can detect growth faltering sooner than less frequent estimates of length, which can lead to timely intervention.
1. A computer-implemented method to estimate growth of a subject, the computer-implemented method comprising:
accessing a plurality of three-dimensional image of a subject captured over a period of time;
generating respective virtual skeletons from the plurality of three-dimensional images of the subject;
determining estimates of a partial length for respective virtual skeletons, generated from the plurality of three-dimensional images of the subject, by measuring a distance between landmarks of the virtual skeletons for each processed image;
comparing the estimates of partial lengths to determine a change in the subject's partial length over time and to provide an indication of growth; and
comparing the indication of growth with a reference growth to determine an advisability of an intervention.
2. The computer-implemented method of claim 1 , wherein the landmarks comprise at least one point of inflection.
3. The computer-implemented method of claim 1 , the method further comprising:
processing the plurality of three-dimensional images of the subject to generate respective point-cloud representations of the subject; and
using the point-cloud representations of the subject to generate respective virtual skeletons.
4. The computer-implemented method of claim 1 , wherein a first of the three-dimensional images of the subject is captured using a time of flight device.
5. The computer-implemented method of claim 1 , wherein a first of the three-dimensional images of the subject is captured using a mobile communication device camera.
6. The computer-implemented method of claim 1 , wherein a first of the three-dimensional images of the subject and a second of the three-dimensional images of the subject are captured within a week of each other.
7. The computer-implemented method of claim 1 wherein a first of the three-dimensional images of the subject comprises an image of the subject and a background of known dimensions, the method further comprising:
acquiring distance values associated with depth information for the first of the three dimensional images of the subject on the background; and
acquiring amplitude values associated with brightness information of reflected light for the first of the three dimensional images of the subject on the background.
8. A system comprising:
one or more computing devices associated with a measurement system, wherein the measurement system is configured to:
access a plurality of three-dimensional image of a subject captured over a period of time;
generate respective virtual skeletons from the plurality of three-dimensional images of the subject;
determine estimates of a partial length for respective virtual skeletons, generated from the plurality of three-dimensional images of the subject, by measuring a distance between landmarks of the virtual skeletons for each processed image;
use the estimates of partial lengths to determine a change in the subject's partial length over time and to provide an indication of growth; and
use the indication of growth and a reference growth to determine an advisability of an intervention.
9. The system of claim 8 , wherein the landmarks comprise at least one point of inflection.
10. The system of claim 8 , wherein the system is further configured to:
process the plurality of three-dimensional images of the subject to generate respective point-cloud representations of the subject; and
use the point-cloud representations of the subject to generate respective virtual skeletons.
11. The system of claim 8 , wherein a first of the three-dimensional images of the subject is captured using a time of flight device.
12. The system of claim 8 , wherein a first of the three-dimensional images of the subject is captured using a mobile communication device camera.
13. The system of claim 8 , wherein a first of the three-dimensional images of the subject and a second of the three-dimensional images of the subject are captured within a week of each other.
14. The system of claim 8 , wherein a first of the three-dimensional images of the subject comprises an image of the subject and a background of known dimensions, the system further configured to:
acquire distance values associated with depth information for the first of the three dimensional images of the subject on the background; and
acquire amplitude values associated with brightness information of reflected light for the first of the three dimensional images of the subject on the background.
15. Computer-readable media that stores instructions, that when executed by a computing device cause the computing device to perform operations comprising:
access a first plurality of three-dimensional image of a subject captured over a period of time;
generate respective virtual skeletons from the first plurality of three-dimensional images of the subject;
determine estimates of at least a partial length for respective virtual skeletons, generated from the plurality of three-dimensional images of the subject, by measuring a distance between landmarks of the virtual skeletons for each processed image;
use the estimates of partial lengths to determine a change in the subject's partial length over time and to provide an indication of growth; and
use the indication of growth and a reference growth to determine an advisability of an intervention.
16. The computer-readable media of claim 15 , wherein the landmarks comprise at least one point of inflection.
17. The computer-readable media of claim 15 , the operations further comprising:
process the first plurality of three-dimensional images of the subject to generate respective point-cloud representations of the subject; and
use the point-cloud representations of the subject to generate respective virtual skeletons.
18. The computer-readable media of claim 15 , wherein a first of the three-dimensional images of the subject is captured using a time of flight device.
19. The computer-readable media of claim 15 , wherein a first of the three-dimensional images of the subject is captured using a mobile communication device camera.
20. The computer-readable media of claim 15 , wherein a first of the three-dimensional images of the subject and a second of the three-dimensional images of the subject are captured within a week of each other.
21. The computer-readable media of claim 15 , wherein a first of the three-dimensional images of the subject comprises an image of the subject and a background of known dimensions, the operations further comprising:
acquire distance values associated with depth information for the first of the three dimensional images of the subject on the background; and
acquire amplitude values associated with brightness information of reflected light for the first of the three dimensional images of the subject on the background.