Hand-gesture recognition method
First Claim
1. A method or providing device inputs, the method comprising:
- illuminating hand gestures performed via a bare hand of a user in a three-dimensional foreground of a background surface with at least one infrared (IR) light source;
generating a first plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface;
generating a second plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand the background surface;
determining a plurality of three-dimensional features of the bare hand relative to the background surface based on a parallax separation of the bare hand in the first plurality of silhouette images relative to the second plurality of silhouette images;
determining a first provided input gesture based on the plurality of three-dimensional features of the bare hand, the provided input gesture comprising the bare hand being positioned in a flat, open hand gesture and being rotated at an associated wrist approximately 180 degrees;
determining a second provided input gesture comprising the flat, open hand gesture being maintained subsequent to rotation of the associated wrist while at least one additional gesture input is performed from one of the bare hand and another bare hand of the user;
comparing the provided first and second input gestures with a plurality of predefined gesture inputs in a gesture library;
providing at least one first device input corresponding to interaction with displayed visual content based on the provided first input gesture corresponding to one of the plurality of predefined gesture inputs, the at least one first device input responsive to the provided first input gesture comprising one of a page-up input and a page-down input associated with a document; and
providing at least one second device input corresponding to interaction with the displayed visual content based on the provided second input gesture corresponding to one of the plurality of predefined gesture inputs, the at least one second device input responsive to the provided second input gesture comprising one of;
scrolling a page of the document one of upwards and downwards in response to the at least one additional gesture input from the bare hand;
repeating at least one of the page-up and the page-down inputs associated with the document in response to the at least one additional gesture input; and
auto-turning a page of the document at one of an acceleration and a deceleration that is based on a duration at which the at least one additional gesture input is maintained.
3 Assignments
0 Petitions
Accused Products
Abstract
One embodiment of the invention includes a method of providing device inputs. The method includes illuminating hand gestures performed via a bare hand of a user in a foreground of a background surface with at least one infrared (IR) light source. The method also includes generating a first plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface and generating a second plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface. The method also includes determining a plurality of three-dimensional features of the bare hand relative to the background surface based on a parallax separation of the bare hand in the first plurality of silhouette images relative to the second plurality of silhouette images. The method also includes determining a provided input gesture based on the plurality of three-dimensional features of the bare hand and comparing the provided input gesture with a plurality of predefined gesture inputs in a gesture library. The method further includes providing at least one device input corresponding to interaction with displayed visual content based on the provided input gesture corresponding to one of the plurality of predefined gesture inputs.
134 Citations
4 Claims
-
1. A method or providing device inputs, the method comprising:
-
illuminating hand gestures performed via a bare hand of a user in a three-dimensional foreground of a background surface with at least one infrared (IR) light source; generating a first plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface; generating a second plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand the background surface; determining a plurality of three-dimensional features of the bare hand relative to the background surface based on a parallax separation of the bare hand in the first plurality of silhouette images relative to the second plurality of silhouette images; determining a first provided input gesture based on the plurality of three-dimensional features of the bare hand, the provided input gesture comprising the bare hand being positioned in a flat, open hand gesture and being rotated at an associated wrist approximately 180 degrees; determining a second provided input gesture comprising the flat, open hand gesture being maintained subsequent to rotation of the associated wrist while at least one additional gesture input is performed from one of the bare hand and another bare hand of the user; comparing the provided first and second input gestures with a plurality of predefined gesture inputs in a gesture library; providing at least one first device input corresponding to interaction with displayed visual content based on the provided first input gesture corresponding to one of the plurality of predefined gesture inputs, the at least one first device input responsive to the provided first input gesture comprising one of a page-up input and a page-down input associated with a document; and providing at least one second device input corresponding to interaction with the displayed visual content based on the provided second input gesture corresponding to one of the plurality of predefined gesture inputs, the at least one second device input responsive to the provided second input gesture comprising one of; scrolling a page of the document one of upwards and downwards in response to the at least one additional gesture input from the bare hand; repeating at least one of the page-up and the page-down inputs associated with the document in response to the at least one additional gesture input; and auto-turning a page of the document at one of an acceleration and a deceleration that is based on a duration at which the at least one additional gesture input is maintained. - View Dependent Claims (2)
-
-
3. A method of providing device inputs, the method comprising:
-
illuminating hand gestures performed via a bare hand of a user in a three-dimensional foreground of a background surface with at least one infrared (IR) light source; generating a first plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface; generating a second plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface; determining a plurality of three-dimensional features of the bare hand relative to the background surface based on a parallax separation of the bare hand in the first plurality of silhouette images relative to the second plurality of silhouette images; determining a provided input gesture based on the plurality of three-dimensional features of the bare hand, the provided input gesture comprising the bare hand switching from a first sub-gesture comprising an extended thumb, and extended index finger, and an extended middle finger to a second sub-gesture comprising a retracted thumb, an extended index finger, and an extended middle finger and is moved one of up, down, left, and right while maintaining the second sub-gesture; comparing the provided input gesture with a plurality of predefined gesture inputs in a gesture library; and providing at least one device input corresponding to interaction with displayed visual content based on the provided input gesture corresponding to one of the plurality of predefined gesture inputs, the at least one device input responsive to the provided input gesture comprising tilting a view one of up and down in response to the movement of the maintained second sub-gesture up and down, respectively, and panning the view one of left and right in response to the movement of the maintained second sub-gesture left and right, respectively.
-
-
4. A method of providing device inputs, the method comprising:
-
illuminating hand gestures performed via a bare hand of a user in a three-dimensional foreground of a background surface with at least one infrared (IR) light source; generating a first plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface; generating a second plurality of silhouette images associated with the bare hand based on an IR light contrast between the bare hand and the background surface; determining a plurality of three-dimensional features of the bare hand relative to the background surface based on a parallax separation of the bare hand in the first plurality of silhouette images relative to the second plurality of silhouette images; determining a provided input gesture based on the plurality of three-dimensional features of the bare hand, the provided input gesture comprising the bare hand of the user pointing at the portion of the displayed visual content with an extended index finger and an extended thumb that is subsequently retracted followed by a rotation of an associated wrist; comparing the provided input gesture with a plurality of predefined gesture inputs in a gesture library; and providing at least one device input corresponding to interaction with displayed visual content based on the provided input gesture corresponding to one of the plurality of predefined gesture inputs, the at least one device input responsive to the provided input gesture comprising tilting a view associated with the displayed visual content in response to the retraction of the thumb, the tilting being based on the rotation of the wrist.
-
Specification