Architecture for controlling a computer using hand gestures
First Claim
1. A computer-implemented system having memory, processor, and data storage subsystems that facilitates a user interface, the computer-implemented system comprising;
- a tracking component to detect motion of a group of moving pixels included in two or more images by employing multiple hypotheses on the two or more images utilizing two or more trackers to track a detected object, such that a second tracker continues tracking the detected object upon failure of a first tracker, wherein the tracking component detects motion when a sum of absolute differences of at least one pixel within the two or more images is above a specified threshold, wherein a vision algorithm comprising 3-D tracking and 3-D depth computations is employed in association with the tracking component;
at least two video capturing sources configured to receive a user command to control the computer-implemented system, wherein the user command is received from a gesture extracted from the group of moving pixels included in the two or more images captured by the at least two video capturing sources; and
a 3-D imaging component that receives the gesture in a form of a gesture image, processes the gesture image, and interprets the gesture image to execute the user command for control of the computer-implemented system via a plurality of object hypothesis models which detect associated multiple objects and remove any redundantly tracked objects.
2 Assignments
0 Petitions
Accused Products
Abstract
A 3-D imaging system for recognition and interpretation of gestures to control a computer. The system includes a 3-D imaging system that performs gesture recognition and interpretation based on a previous mapping of a plurality of hand poses and orientations to user commands for a given user. When the user is identified to the system, the imaging system images gestures presented by the user, performs a lookup for the user command associated with the captured image(s), and executes the user command(s) to effect control of the computer, programs, and connected devices.
406 Citations
22 Claims
-
1. A computer-implemented system having memory, processor, and data storage subsystems that facilitates a user interface, the computer-implemented system comprising;
-
a tracking component to detect motion of a group of moving pixels included in two or more images by employing multiple hypotheses on the two or more images utilizing two or more trackers to track a detected object, such that a second tracker continues tracking the detected object upon failure of a first tracker, wherein the tracking component detects motion when a sum of absolute differences of at least one pixel within the two or more images is above a specified threshold, wherein a vision algorithm comprising 3-D tracking and 3-D depth computations is employed in association with the tracking component; at least two video capturing sources configured to receive a user command to control the computer-implemented system, wherein the user command is received from a gesture extracted from the group of moving pixels included in the two or more images captured by the at least two video capturing sources; and a 3-D imaging component that receives the gesture in a form of a gesture image, processes the gesture image, and interprets the gesture image to execute the user command for control of the computer-implemented system via a plurality of object hypothesis models which detect associated multiple objects and remove any redundantly tracked objects. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer-implemented method for facilitating a user interface, comprising:
-
detecting a first object; tracking the first object based at least in part upon image comparison of a plurality of images relative to a course mapping of the images, the tracking performed in association with multiple object hypotheses utilizing multiple trackers comprising at least a first tracker and a second tracker to select and track the first object based on one or more criteria such that the second tracker continues to track the first object upon failure of the first tracker to track the first object, wherein motion is detected when a sum of absolute differences of at least one pixel within the plurality of images is above a specified threshold, and wherein a vision algorithm comprising 3-D tracking and 3-D depth computations is employed in association with the tracking of the first object; providing iterative seeding in relation to the object hypotheses based at least in part upon a presence of the first object and the image comparison; selectively removing at least one object from the object hypotheses or at least one object hypothesis from the object hypotheses interpreting an object characteristic of the first object; and executing a command in response to the object characteristic. - View Dependent Claims (14, 15, 16, 17)
-
-
18. A computer-implemented system having memory, processor, and data storage subsystems that facilitates a user interface, the computer-implemented system comprising;
-
a tracking component that tracks a first object based at least in part upon image comparison of a plurality of images relative to a course mapping of the images, the tracking performed in association with multiple object hypotheses utilizing multiple trackers comprising at least a first tracker and a second tracker to select and track the first object based on one or more criteria such that the second tracker continues to track the first object upon failure of the first tracker to track the first object, wherein the tracking component detects motion when a sum of absolute differences of at least one pixel within the plurality of images is above a specified threshold, wherein a vision algorithm comprising 3-D tracking and 3-D depth computations is employed in association with the tracking component; a seeding component that iterative seeds the tracking component with object hypotheses based at least in part upon a presence of the first object and the image comparison; a filtering component that selectively removes at least one object from the object hypotheses or at least one object hypothesis from the object hypotheses; and an interpreting component that interprets an object characteristic of the first object and executes a command in response thereto. - View Dependent Claims (19, 20, 21, 22)
-
Specification