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

• US 9,619,039 B2
• Filed: 09/05/2014
• Issued: 04/11/2017
• Est. Priority Date: 09/05/2014
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Whelan, John Desmond
• Primary Examiner(s): MERCEDES, DISMERY E
• Application Number:
  US14/478,475
• Publication Number:
  US 20160070355A1
• Time in Patent Office: 949 Days
• Field of Search: None
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• CPC Class Codes: G06F 12/082 Associative directories G06F12/0822 takes precedence
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• 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 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 collecting, at a computer, motion sensor input data of motions of the individual from a motion sensor for an interval of time. The method further includes analyzing, using the computer, the motion sensor input data using an analysis application having a set of classified predetermined motions of interest. The analysis application classifies a movement captured during the interval of time as a motion corresponding to one of a plurality of pre-determined motions of interest based on shared relative attributes. The method further includes generating an output providing notice of an identified predetermined motion of interest to a monitoring system.

Claims

1. A method for monitoring an individual installing equipment, comprising:

using a motion sensor to monitor an individual when the individual is installing equipment that involves the positions of kneeling, standing or reaching;

collecting, at a computer, motion sensor input data of motions of the individual from a motion sensor for an interval of time, for use in determining qualitative descriptions of positions of the individual;

analyzing, using the computer, the motion sensor input data to classify and identify a position of the individual using an associative memory classification as one of at least standing or kneeling, and to classify a movement captured during the interval of time as a motion corresponding to one of a plurality of pre-determined motions of interest based on shared relative attributes, where the plurality of pre-determined motions includes at least a bending over movement;

generating an output providing notice of an identified predetermined motion of interest to a monitoring system, and

monitoring the duration the individual maintains the identified position, to collect metrics on how long the individual maintains a potentially risky position.

2. The method of claim 1, further comprising:

generating an alarm output when an identified predetermined motion of interest exceeds a predetermined threshold.

3. The method of claim 1 further comprising:

responsive to receiving the notice, collecting metrics on the motion of interest.

4. The method of claim 1 further comprising:

responsive to receiving the notice, collecting metrics on additional movements by the individual.

5. An apparatus for identifying a motion of interest of an individual, comprising:

a motion sensor for monitor an individual when the individual is installing equipment that involves the positions of kneeling, standing or reaching;

a computer in communication with the motion sensor, the computer being configured to collect motion sensor data from the motion sensor on motions of the individual for an interval of time, for use in determining a plurality of qualitative descriptions of positions of the individual;

a non-transitory computer readable storage medium storing an analysis application configured such that when executed by the computer, analyzes the motion sensor data to classify and identify a position of the individual using an associative memory classification as one of at least standing or kneeling, and to classify a movement of the individual captured during the interval of time as a motion corresponding to one of a plurality of predetermined motions of interest based on shared relative attributes, where the plurality of pre-determined motions includes at least a bending over movement; and

wherein the analysis application is further configured, when executed, to generate an output providing notice of an identified predetermined motion of interest to a monitoring system, and to monitor the duration the individual maintains the identified position to collect metrics on how long the individual maintains a potentially risky position.

6. The system of claim 5, wherein the computer is further configured to generate an alarm output when an identified predetermined motion of interest exceeds a pre-determined threshold.

7. The apparatus of claim 5, wherein the computer is further configured, responsive to receiving the notice, to collect metrics on the motion of interest.

8. The apparatus of claim 5, wherein the computer is further configured, responsive to receiving the notice, to collect metrics on additional movements by the individual.

9. A system comprising:

a kinematic measurement device having one or more sensors configured to detect a plurality of physical positions of a part of an object;

an associative memory, in communication with the kinematic measurement device, and 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; and

a processor, in communication with the associative memory and the kinematic measurement device, and configured to use a motion sensor to monitor an individual when the individual is installing equipment that involves the positions of kneeling, standing or reaching;

collect motion sensor input data of motions of the individual from a motion sensor for an interval of time, for use in determining qualitative descriptions of positions of the individual;

analyze the motion sensor input data to classify and identify a position of the individual using an associative memory classification as one of at least standing or kneeling, and to classify a movement captured during the interval of time as a motion corresponding to one of a plurality of pre-determined motions of interest based on shared relative attributes, where the plurality of pre-determined motions includes at least a bending over movement generate an output providing notice of an identified predetermined motion of interest to a monitoring system; and

monitor the duration the individual maintains the identified position, to collect metrics on how long the individual maintains a potentially risky position.

10. The system of claim 9, wherein the processor is further configured to cause the monitoring system to measure additional motions of the object when the particular motion matches the one of the subset of the plurality of pre-determined motions.

11. The system of claim 10, wherein the processor in conjunction with the associative memory is configured to output an assessment of the additional motions the object.

12. The system of claim 11, wherein assessment is based on a criteria selected by a user.

13. The system of claim 10, wherein the object is a person.

14. The system of claim 13, wherein the subset comprises at least one undesirable body position of the person.

15. The system of claim 14, wherein the additional motions comprise all motions of the person during an interval of time.

16. The system of claim 14, wherein the additional motions comprise only those motions that are within the subset during an interval of time.

17. The system of claim 14, wherein an individual body part of the person is monitored.

18. The system of claim 14, wherein the processor is further configured to notify the monitoring system when the motions of the person are no longer in the subset.

19. The system of claim 18, wherein the processor is further configured to command the monitoring system to cease monitoring the person when the motions of the person are outside of the subset.

20. The system of claim 9, wherein the associative memory is configured to be trained to include an additional pre-determined motion within the plurality of pre-determined motions and to include a further motion in the subset of the plurality of pre-determined motions.