Representation of user position, movement, and gaze in mixed reality space
Controlling a mixed reality (MR), virtual reality (VR), or augmented reality (AR) (collectively, MR) environment visualization may involve obtaining a plurality of sensor data from a plurality of data sources; processing the obtained plurality of sensor data using a plurality of data analyzers to identify at least one feature; generating a plurality of annotated data sets, wherein the annotated data sets contain an annotation of the at least one feature; aggregating the plurality of annotated data sets to correlate the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets; and based at least on the common feature, providing a visualization output representing the MR (VR, AR, or specifically mixed-reality) environment. Disclosed examples enable utilizing of disparate data types from different data sources, localizing the different data a common space, and aggregating results for visualization and/or further analysis.
1. A system for controlling a mixed reality (MR) environment visualization, the system comprising:
a processor; and
a computer-readable medium storing instructions that are operative when executed by the processor to:
obtain a plurality of sensor data from a plurality of data sources;
process the obtained plurality of sensor data using a plurality of data analyzers to identify at least one feature;
generate a plurality of annotated data sets, wherein the annotated data sets contain an annotation of the at least one feature;
aggregate the plurality of annotated data sets to correlate the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets; and
based at least on the common feature, provide a visualization output representing the MR environment.
2. The system of claim 1 wherein the instructions are further operative to:
control a display unit, based at least on the visualization output.
3. The system of claim 1 wherein the plurality of sensor data from a plurality of data sources comprises source data from each of a plurality of different sensors.
4. The system of claim 1 wherein the plurality of sensor data from a plurality of data sources comprises at least two selected from the list consisting of:
user position data, user motion data, user gaze data, user-object interaction data, and object manipulation data.
5. The system of claim 1 wherein the plurality of different sensors comprises at least two sensors selected from the list consisting of:
a first camera, a second camera aimed to provide stereo vision with the first camera, a third camera oriented differently than the first camera, a microphone, an accelerometer, a GPS sensor, a photoreceptive light sensor, a keypad, a wearable device, and an inertial measurement unit (IMU).
6. The system of claim 1 wherein correlating the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets comprises using timestamp information to determine a time of the at least one feature within each of two or more of the annotated data sets.
7. The system of claim 1 wherein correlating the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets comprises localizing the at least one feature to a common space within each of two or more of the annotated data sets.
8. A method of controlling a mixed reality (MR) environment visualization, the method comprising:
obtaining a plurality of sensor data from a plurality of data sources;
processing the obtained plurality of sensor data using a plurality of data analyzers to identify at least one feature;
generating a plurality of annotated data sets, wherein the annotated data sets contain an annotation of the at least one feature;
aggregating the plurality of annotated data sets to correlate the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets; and
based at least on the common feature, providing a visualization output representing the MR environment.
9. The method of claim 8 further comprising:
controlling a display unit, based at least on the visualization output.
10. The method of claim 8 wherein the plurality of sensor data from a plurality of data sources comprises source data from each of a plurality of different sensors.
11. The method of claim 8 wherein the plurality of sensor data from a plurality of data sources comprises at least two selected from the list consisting of:
user position data, user motion data, user gaze data, user-object interaction data, and object manipulation data.
12. The method of claim 8 wherein the plurality of different sensors comprises at least two sensors selected from the list consisting of:
a first camera, a second camera aimed to provide stereo vision with the first camera, a third camera oriented differently than the first camera, a microphone, an accelerometer, a GPS sensor, a photoreceptive light sensor, a keypad, a wearable device, and an inertial measurement unit (IMU).
13. The method of claim 8 wherein correlating the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets comprises using timestamp information to determine a time of the at least one feature within each of two or more of the annotated data sets.
14. The method of claim 8 wherein correlating the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets comprises localizing the at least one feature to a common space within each of two or more of the annotated data sets.
15. One or more computer storage devices having computer-executable instructions stored thereon for controlling a mixed reality (MR) environment visualization, which, on execution by a computer, cause the computer to perform operations comprising:
obtaining a plurality of sensor data from a plurality of data sources;
processing the obtained plurality of sensor data using a plurality of data analyzers to identify at least one feature;
generating a plurality of annotated data sets, wherein the annotated data sets contain an annotation of the at least one feature;
aggregating the plurality of annotated data sets to correlate the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets;
based at least on the common feature, providing a visualization output representing the MR environment; and
controlling a display unit, based at least on the visualization output.
16. The one or more computer storage devices of claim 15 wherein the plurality of sensor data from a plurality of data sources comprises source data from each of a plurality of different sensors.
17. The one or more computer storage devices of claim 15 wherein the plurality of sensor data from a plurality of data sources comprises at least two selected from the list consisting of:
user position data, user motion data, user gaze data, user-object interaction data, and object manipulation data.
18. The one or more computer storage devices of claim 15 wherein the plurality of different sensors comprises at least two sensors selected from the list consisting of:
a first camera, a second camera aimed to provide stereo vision with the first camera, a third camera oriented differently than the first camera, a microphone, an accelerometer, a GPS sensor, a photoreceptive light sensor, a keypad, a wearable device, and an inertial measurement unit (IMU).
19. The one or more computer storage devices of claim 15 wherein correlating the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets comprises using timestamp information to determine a time of the at least one feature within each of two or more of the annotated data sets.
20. The one or more computer storage devices of claim 15 wherein correlating the at least one feature as a common feature across different annotated data sets of the plurality of annotated data sets comprises localizing the at least one feature to a common space within each of two or more of the annotated data sets.