Gesture recognizer system architecture
View Patent ↗Systems, methods and computer readable media are disclosed for a gesture recognizer system architecture. A recognizer engine is provided, which receives user motion data and provides that data to a plurality of filters. A filter corresponds to a gesture, that may then be tuned by an application receiving information from the gesture recognizer so that the specific parameters of the gesture—such as an arm acceleration for a throwing gesture—may be set on a per-application level, or multiple times within a single application. Each filter may output to an application using it a confidence level that the corresponding gesture occurred, as well as further details about the user motion data.
1. A method for providing recognition of gestures made by a user using a gesture filter representing a gesture, comprising:
receiving information indicative of a user motion or pose, the information being captured by a camera;
determining from the information that the information is further indicative of a change in the user's fatigue, a change in the user's competence, or a second user replacing the user, and in response, modifying a parameter of the gesture filter;
determining an output of the modified gesture filter based on the information; and
sending the output to an application.
2. The method of claim 1 , further comprising:
receiving second information indicative of a user motion or pose, the second information being captured by the camera;
determining a second output of the gesture filter based on the second information; and
sending the application the second output.
3. The method of claim 1 , further comprising:
receiving second information indicative of sound captured by a microphone; and
sending an indication of the second information to the application.
4. The method of claim 1 , wherein the gesture filter has a plurality of contexts, and a parameter of each context of the base information about the gesture is unique.
5. The method of claim 1 , wherein the gesture filter comprises a second parameter, and further comprising:
in response to receiving second information indicative of a user motion or pose, the information being captured by the camera, receiving from the application a value for the second parameter; and
wherein determining an output of the modified gesture filter based on the information further comprises:
determining an output of the modified gesture filter based on the value for the second parameter.
6. The method of claim 1 , wherein determining the output of the modified gesture filter based on the information further comprises:
determine a confidence level that the information is indicative of the gesture being performed.
7. The method of claim 1 , wherein the gesture comprises:
a crouch, a jump, a lean, an arm throw, a toss, a swing, a dodge, a kick, or a block.
8. The method of claim 1 , wherein a gesture filter comprises a type of input and a type of output, and further comprising:
replacing the gesture filter with a second filter, the second filter having the same type of input and type of output as the gesture filter,
receiving second information captured by a camera;
determining a second output of the second filter based on the second information; and
sending the application the second output.
9. The method of claim 1 , wherein sending the output to the application comprises:
sending the output to the application and a second application.
10. A system for providing recognition of gestures made by a user using a gesture filter representing a gesture comprising:
a processor; and
a memory communicatively coupled to the processor when the system is operational, the memory bearing processor-executable instructions that, when executed by the processor, cause the system at least to:
receive information indicative of a user motion or pose, the information being captured by a camera;
determine from the information that the information is further indicative of a change in the user's fatigue, a change in the user's competence, or a second user replacing the user, and in response, modifying a parameter of the gesture filter;
determine an output of the modified gesture filter based on the information; and
send the output to an application.
11. The system of claim 10 , wherein the gesture filter has a plurality of contexts, and a parameter of each context of the base information about the gesture is unique.
12. The system of claim 10 , wherein the memory further bears processor-executable instructions that, when executed by the processor, cause the system to at least:
receive the gesture filter from the application.
13. The system of claim 10 , wherein the gesture filter comprises a second parameter, and wherein the memory further bears processor-executable instructions that, when executed by the processor, cause the system at least to:
in response to receiving second information indicative of a user motion or pose, the information being captured by the camera, receive from the application a value for the second parameter; and
wherein the processor-executable instructions that, when executed by the system, cause the system to at least determine an output of the modified gesture filter based on the information further cause the system to at least:
determine an output of the modified gesture filter based on the value for the parameter.
14. The system of claim 10 , wherein processor-executable instructions that, when executed by the processor, cause the system at least to determine the output of the gesture filter based on the information further causes the system at least to:
determine a confidence level that the information is indicative of the gesture being performed.
15. The system of claim 10 , wherein the gesture comprises:
a crouch, a jump, a lean, an arm throw, a toss, a swing, a dodge, a kick, or a block.
16. The system of claim 10 , wherein a gesture filter comprises a type of input and a type of output, and wherein the memory further bears processor-executable instructions that, when executed by the processor, cause the system at least to:
replace the gesture filter with a second filter, the second filter having the same type of input and type of output as the gesture filter,
receive second information captured by a camera;
determine a second output of the second filter based on the second information; and
send the application the second output.
17. The system of claim 10 , wherein the memory further bears processor-executable instructions that, when executed by the processor, cause the system at least to:
receive sound information; and
wherein the processor-executable instructions that, when executed by the system, cause the system to at least determine an output of the second gesture filter based on the information further cause the system to at least:
determining the output of the second gesture filter based on the sound information.
18. The system of claim 10 , wherein processor-executable instructions that, when executed by the processor, cause the system at least to send the output to the application further causes the system at least to:
send the output to the application and a second application.
19. A computer-readable storage medium for providing recognition of gestures made by a user using a gesture filter representing a gesture bearing computer-readable instructions that, when executed on a computer, cause the computer to perform operations comprising:
receiving data indicative of a user motion or pose, the data being captured by a camera;
determine from the information that the information is further indicative of a change in the user's fatigue, a change in the user's competence, or a second user replacing the user, and in response, modifying a parameter of the gesture filter;
determine an output of the modified gesture filter based on the information; and
sending the output to an application.
20. The computer-readable storage medium of claim 19 , wherein sending the output to the application comprises:
sending the output to the application and a second application.