Real time hand tracking, pose classification, and interface control
First Claim
Patent Images
1. A method of controlling an electronics device via hand gestures, comprising:
- detecting, via an image processing module of the electronics device, a bare-hand position via a camera input based upon a detected sequence of bare-hand positions;
determining whether the bare-hand position has been detected for a threshold duration of time;
identifying the detected bare-hand position from a vocabulary of hand gestures by;
measuring brightness gradients in multiple directions across a plurality of images captured by the camera;
generating image pyramids from measured brightness gradients of the extracted hand gesture;
extracting pixel intensity/displacement features and scale invariant feature transform (SIFT) features using the generated pyramids;
applying a cascade filter in association with extracting the pixel intensity/displacement features and the SIFT features from the generated image pyramids;
classifying a hand pose type using a trained multiclass support vector machine (SVM); and
determining the hand gesture by a distance calculation that calculates and selects a closest gesture in the vocabulary of hand gestures, where the closest gesture comprises a gesture with hand joints closest to the hand joints in the vocabulary of gestures;
where the identified bare-hand position comprises a hand gesture associated with powering on the electronics device; and
controlling, in response to determining that the bare-hand position has been detected for the threshold duration of time, the electronics device in response to the identified bare-hand position by powering on the electronics device.
0 Assignments
0 Petitions
Accused Products
Abstract
A hand gesture from a camera input is detected using an image processing module of a consumer electronics device. The detected hand gesture is identified from a vocabulary of hand gestures. The electronics device is controlled in response to the identified hand gesture. This abstract is not to be considered limiting, since other embodiments may deviate from the features described in this abstract.
-
Citations
22 Claims
-
1. A method of controlling an electronics device via hand gestures, comprising:
-
detecting, via an image processing module of the electronics device, a bare-hand position via a camera input based upon a detected sequence of bare-hand positions; determining whether the bare-hand position has been detected for a threshold duration of time; identifying the detected bare-hand position from a vocabulary of hand gestures by; measuring brightness gradients in multiple directions across a plurality of images captured by the camera; generating image pyramids from measured brightness gradients of the extracted hand gesture; extracting pixel intensity/displacement features and scale invariant feature transform (SIFT) features using the generated pyramids; applying a cascade filter in association with extracting the pixel intensity/displacement features and the SIFT features from the generated image pyramids; classifying a hand pose type using a trained multiclass support vector machine (SVM); and determining the hand gesture by a distance calculation that calculates and selects a closest gesture in the vocabulary of hand gestures, where the closest gesture comprises a gesture with hand joints closest to the hand joints in the vocabulary of gestures; where the identified bare-hand position comprises a hand gesture associated with powering on the electronics device; and controlling, in response to determining that the bare-hand position has been detected for the threshold duration of time, the electronics device in response to the identified bare-hand position by powering on the electronics device. - View Dependent Claims (2)
-
-
3. A method of controlling an electronics device via hand gestures, comprising:
-
detecting, via an image processing module of the electronics device, a hand gesture via a camera input; identifying the detected hand gesture from a vocabulary of hand gestures by; measuring brightness gradients in multiple directions across a plurality of images captured by the camera; generating image pyramids from measured brightness gradients of the extracted hand gesture; extracting pixel intensity/displacement features and scale invariant feature transform (SIFT) features using the generated pyramids; applying a cascade filter in association with extracting the pixel intensity/displacement features and the SIFT features from the generated image pyramids; classifying a hand pose type using a trained multiclass support vector machine (SVM); and determining the hand gesture by a distance calculation that calculates and selects a closest gesture in the vocabulary of hand gestures, where the closest gesture comprises a gesture with hand joints closest to the hand joints in the vocabulary of gestures; and controlling the electronics device in response to the identified hand gesture. - View Dependent Claims (4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. An apparatus for controlling an electronics device via hand gestures, comprising:
-
a camera; and a processor programmed to; detect a bare-hand position via the camera based upon a detected sequence of bare-hand positions; determine whether the bare-hand position has been detected for a threshold duration of time; identify the detected bare-hand position from a vocabulary of hand gestures by; measuring brightness gradients in multiple directions across a plurality of images captured by the camera; generating image pyramids from measured brightness gradients of the extracted hand gesture; extracting pixel intensity/displacement features and scale invariant feature transform (SIFT) features using the generated pyramids; applying a cascade filter in association with extracting the pixel intensity/displacement features and the SIFT features from the generated image pyramids; classifying a hand pose type using a trained multiclass support vector machine (SVM); and determining the hand gesture by a distance calculation that calculates and selects a closest gesture in the vocabulary of hand gestures, where the closest gesture comprises a gesture with hand joints closest to the hand joints in the vocabulary of gestures; where the identified bare-hand position comprises a hand gesture associated with powering on the electronics device; and control, in response to determining that the bare-hand position has been detected for the threshold duration of time, the electronics device in response to the identified bare-hand position by powering on the electronics device.
-
-
14. An apparatus for controlling an electronics device via hand gestures, comprising:
-
a camera; and a processor programmed to; detect a hand gesture via the camera; identify the detected hand gesture from a vocabulary of hand gestures by; measuring brightness gradients in multiple directions across a plurality of images captured by the camera; generating image pyramids from measured brightness gradients of the extracted hand gesture; extracting pixel intensity/displacement features and scale invariant feature transform (SIFT) features using the generated pyramids; applying a cascade filter in association with extracting the pixel intensity/displacement features and the SIFT features from the generated image pyramids; classifying a hand pose type using a trained multiclass support vector machine (SVM); and determining the hand gesture by a distance calculation that calculates and selects a closest gesture in the vocabulary of hand gestures, where the closest gesture comprises a gesture with hand joints closest to the hand joints in the vocabulary of gestures; and control the electronics device in response to the identified hand gesture. - View Dependent Claims (15, 16, 17, 18, 19, 20, 21, 22)
-
Specification