Behavior recognition system

Patent metadata

Field	Value
Publication number	US-9304593-B2
Application number	US-201313850896-A
Country	US
Kind code	B2
Filing date	Mar 26, 2013
Priority date	Aug 10, 1998
Publication date	Apr 5, 2016
Grant date	Apr 5, 2016

Abstract

A system for recognizing various human and creature motion gaits and behaviors is presented. These behaviors are defined as combinations of “gestures” identified on various parts of a body in motion. For example, the leg gestures generated when a person runs are different than when a person walks. The system described here can identify such differences and categorize these behaviors. Gestures, as previously defined, are motions generated by humans, animals, or machines. Multiple gestures on a body (or bodies) are recognized simultaneously and used in determining behaviors. If multiple bodies are tracked by the system, then overall formations and behaviors (such as military goals) can be determined.

First claim

We claim:

1. A method of controlling a device without touching it, comprising the steps of:
storing a dynamic motion model including gesture information collected over time, the stored model including information describing a particular dynamic gesture to be recognized in the form {dot over (x)}=f(x, θ) where {dot over (x)} is a vector describing the position and velocity components of the gesture and θ is a tunable parameter;
sensing a human motion to be recognized;
extracting position and velocity components of the sensed motion;
determining if the motion is a recognizable gesture based upon the extracted position and velocity components and tunable parameters of the sensed motion; and
if the motion represents a recognizable gesture, generating a command to control a device in accordance with the recognized gesture.

2. The method of claim 1 , wherein the step of sensing includes an electromechanical process using an electrogoniometer or electrogoniometric system.

3. The method of claim 2 , wherein the electromechanical process uses passive reflective or actively illuminated markers to calculate positions or velocities.

4. The method of claim 2 , wherein the electromechanical process uses force data gathered from a force plate or force dynamometer.

5. The method of claim 2 , wherein the electromechanical process uses strain gauge or piezoelectronic transducers.

6. The method of claim 1 , including the step of classifying the gesture as a static gesture if the slowness of the motion falls below a predetermined threshold.

7. The method of claim 1 , wherein the device is a virtual-reality simulator or game.

8. The method of claim 1 , wherein the device is a self-service machine.

9. The method of claim 1 , wherein the device forms part of a robot.

10. The method of claim 1 , wherein the device forms part of a commercial appliance.

11. The method of claim 1 , wherein the step of sensing includes the use of a computer vision system.

12. A gesture-controlled device, comprising:
a sensor for capturing a human gesture to be recognized;
a processor executing a feature tracking algorithm that outputs position and velocity components associated with the captured gesture;
a gesture identification module that converts the position and velocity components into parameters representing a static or dynamic gesture;
wherein the identification of a dynamic gesture is based on a stored dynamic motion model including gesture information collected over time, including information describing a particular dynamic gesture to be recognized in the form {dot over (x)}=f(x, θ) where {dot over (x)} is vector describing the position and velocity components of the gesture and θ is a tunable parameter; and
control apparatus that controls the operation of the device in accordance with the static or dynamic gesture.

13. The gesture-controlled device of claim 12 , wherein the sensor is an electromechanical device.

14. The gesture-controlled device of claim 12 , wherein the sensor uses passive reflective or actively illuminated markers to calculate positions or velocities.

15. The gesture-controlled device of claim 12 , wherein the gesture identification module is operative to classify the gesture as a static gesture if the slowness of the motion falls below a predetermined threshold.

16. The gesture-controlled device of claim 12 , wherein the device is a virtual-reality simulator or game.

17. The gesture-controlled device of claim 12 , wherein the device is a self-service machine or robot.

18. The gesture-controlled device of claim 12 , wherein the device is a commercial appliance.

19. The gesture-controlled device of claim 12 , wherein the sensor is an image sensor.

Assignees

• Cybernet Systems Corp

Inventors

• Cohen Charles J
• Beach Glenn J
• Cavell Brook
• Foulk Eugene
• Jacobus Charles J
• Obermark Jay
• Paul George V

Classifications

• G06V40/25 Primary

  Recognition of walking or running movements, e.g. gait recognition · CPC title

• G06F3/017 Primary

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G06K9/00348

  Physics · mapped topic

• G06K9/00355

  Physics · mapped topic

• G06V40/28

  Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113) · CPC title