Obtaining metrics for a position using frames classified by an associative memory

• US 9,911,031 B2
• Filed: 12/17/2014
• Issued: 03/06/2018
• Est. Priority Date: 09/05/2014
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Whelan, John Desmond, Hancock, Glenn Alan
• Primary Examiner(s): MERCEDES, DISMERY E
• Application Number:
  US14/573,591
• Publication Number:
  US 20160070958A1
• Time in Patent Office: 1,175 Days
• CPC Class Codes: A61B 2503/20 Workers
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G06F 12/082 Associative directories G06F12/0822 takes precedence
• CPC Class Codes: G06F 12/0822 Copy directories local copy tags for implementing a bus snooping protocol G06F12/0831
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06F 18/245 relating to the decision surface
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06T 1/60 Memory management
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

A method for identifying a motion of interest of an individual. The method includes receiving input data from a non-invasive motion sensor measuring movements of a person. The method also includes collecting motion sensor data for an interval of time. The illustrative embodiments also provide for analyzing the motion sensor input data using an analysis application having a set of classified pre-determined motions. The analysis application classifies a movement captured during the interval of time as a motion corresponding to particular a pre-determined motion among a plurality of pre-determined motions. Classification is performed based on shared relative values among the motion sensor input data and the particular pre-determined motion. The illustrative embodiments also provide for generating an output that provides a translation of the movement for identification of a predetermined motion of interest that represents an undesirable ergonomic aspect.

Claims

1. A method for improving ergonomic movements of a person operating factory equipment at a factory, comprising:

receiving input data from a non-invasive motion sensor measuring movements of the person while the person operates the factory equipment;

collecting, using the non-invasive motion sensor, motion sensor data of the movements of the person for an interval of time;

analyzing the motion sensor data using an analysis application having a set of classified pre-determined motions, where the analysis application classifies a movement captured during the interval of time as a motion corresponding to particular a pre-determined motion among a plurality of pre-determined motions, wherein classification is performed based on shared relative values among the motion sensor data and the particular pre-determined motion, wherein a classified motion is formed, and wherein the shared relative values comprise qualitative descriptions of the movements of the person as opposed to quantitative measurements of the movements of the person

comparing the classified motion to a set of pre-determined motions that were pre-determined to be undesirable ergonomic motions in an ergonomic analysis for a factory setting; and

responsive to the classified motion being among the pre-determined motions that were pre-determined to be undesirable ergonomic motions, monitoring an amount of time for the classified motion, and, using a display to display information to the person and issuing an alert that communicates to the person that the pre-determined motion during the interval of time represents an ergonomically incorrect or undesirable movement for a factory setting.

2. The method of claim 1 further comprising:

generating an alert output when the classified motion exceeds a predetermined threshold.

3. The method of claim 1 further comprising:

operating, by the person, the factory equipment.

4. The method of claim 3, wherein, analyzing further comprises:

converting the motion sensor data into word-like verbiage describing points of articulation of the person, and wherein the shared relative values are additional word-like verbiage describing the points of articulation for the plurality of pre-determined motions, such that analyzing is performed by comparing the word-like verbiage to the additional word-like verbiage.

5. The method of claim 1, wherein the analysis application comprises an associative memory comprising a plurality of data and a plurality of associations among the plurality of data, wherein the plurality of data is collected into associated groups, wherein the associative memory is configured to be queried based on at least indirect relationships among the plurality of data.

6. The method of claim 1 further comprising:

including the classified motion as a second pre-determined motion in the plurality of pre-determined motions; and

receiving second input data from the non-invasive motion sensor;

collecting second motion sensor data for a second interval of time;

analyzing the second motion motion sensor data using the analysis application, where the analysis application classifies a second movement captured during the second interval of time as a second motion corresponding to a second pre-determined motion among the plurality of pre-determined motions, wherein classification is performed based on shared relative values among the second motion motion sensor data and the second pre-determined motion, wherein a second classified motion is formed;

comparing the classified motion to a set of pre-determined motions that were pre-determined to be undesirable ergonomic motions in an ergonomic analysis for a factory setting; and

responsive to the classified motion being among the pre-determined motions, using a display to display information to the person and issuing an alert that communicates to the person that the pre-determined motion represents an ergonomically incorrect or undesirable movement for a factory setting.

7. The method of claim 1 further comprising:

determining a level of the undesirable ergonomic motion.

8. The method of claim 7 further comprising:

responsive to the level of the undesirable ergonomic motion exceeding a threshold, notifying a user that the level of the undesirable ergonomic motion has exceeded a threshold.

9. The method of claim 1 further comprising:

providing an output of the analysis application to an ergonomic tool.

10. The method of claim 9 further comprising:

using the ergonomic tool to assess an overall level of ergonomic issues for the person.

11. The method of claim 1 further comprising:

training the analysis application to include the motion in the plurality of pre-determined motions.

12. An apparatus for identifying a body position of interest of an individual, comprising:

a non-invasive body position sensor;

a processor in communication with the body position sensor, being configured to collect body position sensor data of a person for an interval of time; and

an associative memory configured to analyze the body position sensor data, the associative memory storing a set of classified pre-determined body positions, where the associative memory is configured to classify a movement captured during the interval of time as a body position corresponding to a particular pre-determined body position among a plurality of pre-determined body positions, wherein a classified body position is formed, and wherein the associative memory is further configured to compare the classified body position to a set of pre-determined body positions that were pre-determined to be undesirable ergonomic body positions in an ergonomic analysis for a factory setting, and to monitor an amount of time spent in the classified body position, and wherein the associative memory is further configured, responsive to the classified body position during the interval of time being among the set of pre-determined body positions, to use a display to display information to the person and issue an alert that communicates to the person that the pre-determined body position represents an ergonomically incorrect or undesirable movement for a factory setting, and wherein the associative memory is further configured to compare the classified body position by comparing shared qualitative descriptions of body positions of the individual to qualitative descriptions of the set of pre-determined body positions, as opposed to comparing quantitative measurements of the body positions of the individual to quantitative pre-determined body positions.

13. The apparatus of claim 12 further comprising:

an output device configured to generate an output that provides a translation of the movement for identification of a predetermined body position of interest that represents an undesirable ergonomic movement.

14. The apparatus of claim 13, further comprising:

a physical alert device that triggers when the movement exceeds a pre-determined ergonomic threshold.

15. The apparatus of claim 13 further comprising:

an ergonomic tool configured to ergonomically evaluate movements of the person, wherein the ergonomic tool receives as input the output of the output device.

16. The apparatus of claim 13, wherein the output device is configured to notify, responsive to the undesirable ergonomic movement exceeding a threshold, a user that a level of the undesirable ergonomic movement has exceeded a threshold.