Behavior recognition system
First 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.
3 Assignments
0 Petitions
Accused Products
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.
-
Citations
19 Claims
-
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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
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; andcontrol apparatus that controls the operation of the device in accordance with the static or dynamic gesture. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19)
-
Specification