Systems and methods for adaptive gesture recognition

• US 9,785,335 B2
• Filed: 12/27/2010
• Issued: 10/10/2017
• Est. Priority Date: 12/27/2010
• Status: Active Grant

• Current Assignee: Sling Media LLC (Dish Network Corporation)
• Original Assignee: Sling Media Incorporated (Dish Network Corporation)
• Inventors: Oh, Andy
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Heffington, John M
• Application Number:
  US12/978,949
• Publication Number:
  US 20120167017A1
• Time in Patent Office: 2,479 Days
• Field of Search: 715863, 715822
• CPC Class Codes: G01C 21/3664 Details of the user input interface, e.g. buttons, knobs or sliders, including those provided on a touch screen; remote controllers; input using gestures
• CPC Class Codes: G05B 2219/35444 Gesture interface, controlled machine observes operator, executes commands
• CPC Class Codes: G06F 2203/04808 Several contacts: gestures triggering a specific function, e.g. scrolling, zooming, right-click, when the user establishes several contacts with the surface simultaneously; e.g. using several fingers or a combination of fingers and pen
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: H04N 1/00381 Input by recognition or interpretation of visible user gestures manual input means, e.g. digitisers, writing tablets H04N1/00392; gesture input to computers G06F3/017; recognition algorithms G06V40/20

Abstract

Systems and methods are described for adaptively recognizing gestures indicated by user inputs received from a touchpad, touchscreen, directional pad, mouse or other multi-directional input device. If a user'"'"'s movement does not indicate a gesture using current gesture recognition parameters, additional processing can be performed to recognize the gesture using other factors. The gesture recognition parameters can then be adapted so that subsequent user inputs that are similar to the previously-rejected inputs will appropriately trigger gesture commands as desired by the user. Gestural data or parameters may be locally or remotely stored for further processing.

Claims

1. A method to process user inputs received from a multi-directional input device, the method comprising:

receiving at least one of the user inputs from the multi-directional input device, the at least one of the user inputs defining an original movement by a user;

determining if the at least one user input forms a gesture based upon a set of parameters, wherein the parameters outline a confined two-dimensional spatial region of the multi-directional input device that defines the gesture;

if the at least one user input does not form the gesture based upon the two-dimensional spatial region that defines the gesture, attempting to recognize the gesture based upon non-spatial factors that are different from the set of parameters; and

if the gesture is recognized based upon the non-spatial factors, adapting at the two-dimensional spatial region of the multi-directional input device that defines the gesture based upon the at least one user input so that the confined two-dimensional spatial region of the multi-directional input device that defines the gesture is changed to include the original movement by the user.

2. The method of claim 1 further comprising associating the adapted two-dimensional spatial region with each of a plurality of users and storing the adapted two-dimensional spatial region associated with each user in a storage as user-specific data.

3. The method of claim 2 further comprising retrieving the user specific data associated with the particular user prior to performing subsequent determination of gestures formed by subsequent user inputs by the same one of the plurality of users, and using the user specific data associated with the particular user as the non-spatial data in subsequent gesture recognition.

4. The method of claim 2 wherein the adapted two-dimensional spatial region is stored at a remotely-located server system accessible via a network.

5. The method of claim 4 further comprising retrieving the two-dimensional spatial region from the remotely-located server system prior to the determining.

6. The method of claim 1 further comprising issuing a user command in response to the gesture if the gesture is recognized from either the set of parameters or the non-spatial factors.

7. The method of claim 1 wherein the non-spatial factors comprise subsequent actions taken by the user.

8. The method of claim 1 wherein the non-spatial factors comprise a setting in which the user inputs are received.

9. The method of claim 1 wherein the non-spatial factors comprise subsequent user inputs received after the at least one user input.

10. The method of claim 1 wherein the set of parameters comprises a distance travelled for at least one gesture, and wherein the adapting comprises shortening the distance travelled for the at least one gesture based upon the non-spatial factors.

11. The method of claim 1 wherein the shortening comprises setting a new distance based upon a distance travelled in the at least one user input.

12. A computing system comprising:

an input device having a multi-directional sensing region, wherein the input device is configured to sense user inputs relative to a multi-directional sensing region that are applied by a user and to provide output signals indicative of the sensed user inputs; and

a processor configured to receive the output signals from the input device and to initially recognize gestures made by the particular user from at least some of the sensed user inputs indicated in the output signals based upon confined two-dimensional regions of the input device that each correspond to one of the gestures, and, when the user inputs applied by the particular user are not initially recognized, the processor attempting to recognize the gesture based upon user-specific gesture data previously-stored for that particular user, and to adapt the confined two-dimensional regions of the input device corresponding to at least one gesture for that particular user based upon the previously-received user inputs so that the confined two-dimensional region of the input device corresponding to the at least one gesture subsequently includes the user input previously applied by the particular user.

13. The computing system of claim 12 further comprising a network interface configured to facilitate communication on a network, and wherein the processor is configured to communicate with a server on the network via the network interface.

14. The computing system of claim 13 wherein the processor is further configured to provide at least some of the sensed user inputs to the server on the network to thereby allow the server to adapt at least some of the parameters in response to the sensed user inputs, and wherein the processor is further configured to receive the adapted set of parameters from the server on the network.

15. The computing system of claim 14 the set of parameters received from the server on the network is adapted based upon user inputs provided by a plurality of different users each operating a different one of a plurality of computing systems.

16. The computing system of claim 12 wherein the adapted set of parameters is associated with the particular user of a plurality of users and stored in a data storage, and wherein the adapted set of parameters are retrieved from the data storage for subsequent use of the computing system by the particular one of the plurality of users.

17. A computer-executable method to process user inputs obtained from at least one multi-directional input device, the method comprising:

receiving a set of parameters that defines one or more confined two-dimensional regions of the multi-directional input device, each of the confined two-dimensional regions corresponding to one of the one or more two-dimensional gestures applied to the multi-directional input device;

receiving the user inputs;

recognizing at least some of the user inputs as two-dimensional gestures by comparing the user inputs to the set of parameters;

identifying at least some of the user inputs as two-dimensional gestures based upon non-spatial factors that are different than the set of parameters;

adapting the set of parameters based upon the identified user inputs to create an adapted set of parameters in which the confined two-dimensional regions of the multi-directional input device corresponding to the two-dimensional gestures are changed to subsequently include the identified user inputs; and

storing the adapted set of parameters for subsequent retrieval.

18. The method of claim 17 wherein the method is executable by a server that receives the user inputs from each of a plurality of computing systems and that provides the adapted set of parameters to each of the plurality of computing systems via a network.

19. The method of claim 17 wherein the method is executable by a processor in a computing system that comprises the at least one multi-directional input device, wherein the adapted set of parameters is associated with a particular one of a plurality of users of the computing system, and wherein the processor is configured to recognize gestures in subsequent user inputs made by the same particular user of the computing system based upon the adapted set of parameters associated with that particular user.

20. The method of claim 17 wherein the identifying comprises comparing at least some of the user inputs to subsequently-received user inputs that were recognized as gestures.