Periodic parameter estimation for visual-inertial tracking systems
A method for calibrating a visual-inertial tracking system is described. A device operates the visual-inertial tracking system without receiving a tracking request from a virtual object display application. In response to operating the visual-inertial tracking system, the device accesses sensor data from sensors at the device. The device identifies, based on the sensor data, a first calibration parameter value of the visual-inertial tracking system and stores the first calibration parameter value. The system detects a tracking request from the virtual object display application. In response to the tracking request, the system accesses the first calibration parameter value and determines a second calibration parameter value from the first calibration parameter value.
1 . A method comprising:
detecting a calibration trigger event at a wearable device;
in response to detecting the calibration trigger event, identifying, at the wearable device, a first calibration parameter value based on sensor data from a sensor of the wearable device;
storing the first calibration parameter value in a memory of the wearable device;
detecting a tracking request from an application at the wearable device; and
in response to detecting the tracking request, using the first calibration parameter value as a starting point for estimating a second calibration parameter value of a visual-inertial tracking system of the wearable device.
2 . The method of claim 1 , wherein updating the first calibration parameter value is performed during an offline calibration parameter estimation of the visual-inertial tracking system, the offline calibration parameter estimation performed after an online calibration parameter estimation.
3 . The method of claim 2 , further comprising:
in response to detecting the tracking request, switching the offline calibration parameter estimation of the visual-inertial tracking system to the online calibration parameter estimation and using the first calibration parameter value as the starting point for estimating the second calibration parameter value of the visual-inertial tracking system.
4 . The method of claim 1 , wherein detecting the calibration trigger event comprises:
identifying a sensor threshold corresponding to the sensor; and
determining that the sensor data exceeds the sensor threshold.
5 . The method of claim 1 , wherein the calibration trigger event comprises at least one of a temperature change exceeding a temperature threshold, an accelerometer change exceeding an accelerometer threshold, or a battery level transgressing a battery threshold.
6 . The method of claim 1 , wherein detecting the calibration trigger event comprises:
detecting that the wearable device is worn by a user.
7 . The method of claim 1 , further comprising:
operating, absent a tracking request, the visual-inertial tracking system by periodically accessing the sensor data from the sensor of the wearable device;
periodically updating, at the wearable device, the first calibration parameter value based on the sensor data; and
storing, in the memory of the wearable device, the updated first calibration parameter value.
8 . The method of claim 1 , further comprising:
turning off the visual-inertial tracking system after storing the first calibration parameter value at the wearable device; and
activating the visual-inertial tracking system in response to detecting the tracking request from the application.
9 . The method of claim 1 , further comprising:
calibrating the visual-inertial tracking system with the first calibration parameter value before operating the application or with the second calibration parameter value after detecting the tracking request from the application.
10 . The method of claim 1 , wherein the application comprises an augmented reality application.
11 . A wearable device comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the wearable device to perform operations comprising:
detecting a calibration trigger event at a wearable device;
in response to detecting the calibration trigger event, identifying, at the wearable device, a first calibration parameter value based on sensor data from a sensor of the wearable device;
storing the first calibration parameter value in a memory of the wearable device;
detecting a tracking request from an application at the wearable device; and
in response to detecting the tracking request, using the first calibration parameter value as a starting point for estimating a second calibration parameter value of a visual-inertial tracking system of the wearable device.
12 . The wearable device of claim 11 , wherein updating the first calibration parameter value is performed during an offline calibration parameter estimation of the visual-inertial tracking system, the offline calibration parameter estimation performed after an online calibration parameter estimation.
13 . The wearable device of claim 12 , wherein the operations further comprise:
in response to detecting the tracking request, switching the offline calibration parameter estimation of the visual-inertial tracking system to the online calibration parameter estimation and using the first calibration parameter value as the starting point for estimating the second calibration parameter value of the visual-inertial tracking system.
14 . The wearable device of claim 11 , wherein detecting the calibration trigger event comprises:
identifying a sensor threshold corresponding to the sensor; and
determining that the sensor data exceeds the sensor threshold.
15 . The wearable device of claim 11 , wherein the calibration trigger event comprises at least one of a temperature change exceeding a temperature threshold, an accelerometer change exceeding an accelerometer threshold, or a battery level transgressing a battery threshold.
16 . The wearable device of claim 11 , wherein detecting the calibration trigger event comprises:
detecting that the wearable device is worn by a user.
17 . The wearable device of claim 11 , wherein the operations further comprise:
operating, absent a tracking request, the visual-inertial tracking system by periodically accessing the sensor data from the sensor of the wearable device;
periodically updating, at the wearable device, the first calibration parameter value based on the sensor data; and
storing, in the memory of the wearable device, the updated first calibration parameter value.
18 . The wearable device of claim 11 , wherein the operations further comprise:
turning off the visual-inertial tracking system after storing the first calibration parameter value at the wearable device; and
activating the visual-inertial tracking system in response to detecting the tracking request from the application.
19 . The wearable device of claim 11 , wherein the operations further comprise:
calibrating the visual-inertial tracking system with the first calibration parameter value before operating the application or with the second calibration parameter value after detecting the tracking request from the application.
20 . A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform operations comprising:
detecting a calibration trigger event at a wearable device;
in response to detecting the calibration trigger event, identifying, at the wearable device, a first calibration parameter value based on sensor data from a sensor of the wearable device;
storing the first calibration parameter value in a memory of the wearable device;
detecting a tracking request from an application at the wearable device; and
in response to detecting the tracking request, using the first calibration parameter value as a starting point for estimating a second calibration parameter value of a visual-inertial tracking system of the wearable device.