Estimating pose for a client device using a pose prior model
An online system uses a pose prior model and a pose objective function to estimate the pose of a client device. A pose prior model is a model for prior information known about client devices and their poses without reference to a particular client device and its pose data. The online system receives pose data from a client device and computes an estimated pose for the client device based on the received pose data, the pose prior model, and a generated initial candidate pose for the client device. The online system uses these as inputs to a pose objective function and optimizes the pose objective function to estimate a pose for the client device. The online system transmits this estimated pose to the client device, and may use the estimated pose as the pose for the client device for the purposes of delivering content to the user.
1. A method comprising:
obtaining pose data describing a pose of a client device, wherein the pose data comprises a plurality of measurements captured by sensors of the client device;
accessing a pose prior model that represents probabilities that the client device has possible poses;
generating an initial candidate pose for the client device based on the received pose data;
computing an estimated pose for the client device based on a pose objective function, wherein the pose objective function takes, as inputs, pose data describing a pose of a client device, the pose prior model, and the initial candidate pose, wherein computing the estimated pose for the client device comprises optimizing the pose objective function based on the received pose data, the pose prior model, and the initial candidate pose for the client device; and
providing the estimated pose for use in displaying augmented reality content.
2. The method of claim 1 , wherein the pose prior model is based on historical poses of other client devices but does not include pose data for the other client devices.
3. The method of claim 1 , wherein the pose data comprises a measurement captured by a magnetometer, an inertial measurement unit, or a global positioning system sensor.
4. The method of claim 1 , wherein the pose data comprises visual positioning data from a visual positioning system operating on the client device.
5. The method of claim 1 , wherein accessing the pose prior model comprises:
identifying a geographic region within which the client device is located based on the pose data; and
accessing a local pose prior model corresponding to the geographic region.
6. The method of claim 5 , further comprising:
generating the local pose prior model based on historical poses of a plurality of client devices located within the geographic region corresponding to the local pose prior model.
7. The method of claim 1 , wherein generating the initial candidate pose comprises:
randomly generating an initial candidate pose based on the received pose data.
8. The method of claim 1 , wherein generating the initial candidate pose comprises:
receiving an estimated pose from a visual positioning system of the client device.
9. The method of claim 1 , wherein optimizing the pose objective function comprises:
applying an optimization algorithm to the pose objective function.
10. The method of claim 9 , wherein applying the optimization algorithm comprises:
iteratively adjusting intermediary candidate poses based on the pose objective function to compute the estimated pose of the client device.
11. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
obtaining pose data describing a pose of a client device, wherein the pose data comprises a plurality of measurements captured by sensors of the client device;
accessing a pose prior model that represents probabilities that the client device has possible poses;
generating an initial candidate pose for the client device based on the received pose data;
computing an estimated pose for the client device based on a pose objective function, wherein the pose objective function takes, as inputs, pose data describing a pose of a client device, the pose prior model, and the initial candidate pose, wherein computing the estimated pose for the client device comprises optimizing the pose objective function based on the received pose data, the pose prior model, and the initial candidate pose for the client device; and
providing the estimated pose for use in displaying augmented reality content.
12. The computer-readable medium of claim 11 , wherein the pose prior model is based on historical poses of other client devices but does not include pose data for the other client devices.
13. The computer-readable medium of claim 11 , wherein the pose data comprises a measurement captured by a magnetometer, an inertial measurement unit, or a global positioning system sensor.
14. The computer-readable medium of claim 11 , wherein the pose data comprises visual positioning data from a visual positioning system operating on the client device.
15. The computer-readable medium of claim 11 , wherein accessing the pose prior model comprises:
identifying a geographic region within which the client device is located based on the pose data; and
accessing a local pose prior model corresponding to the geographic region.
16. The computer-readable medium of claim 15 , further storing instructions that, when executed by a processor, cause a processor to perform operations comprising:
generating the local pose prior model based on historical poses of a plurality of client devices located within the geographic region corresponding to the local pose prior model.
17. The computer-readable medium of claim 11 , wherein generating the initial candidate pose comprises:
randomly generating an initial candidate pose based on the received pose data.
18. The computer-readable medium of claim 11 , wherein generating the initial candidate pose comprises:
receiving an estimated pose from a visual positioning system of the client device.
19. The computer-readable medium of claim 11 , wherein optimizing the pose objective function comprises:
applying an optimization algorithm to the pose objective function.
20. The computer-readable medium of claim 19 , wherein applying the optimization algorithm comprises:
iteratively adjusting intermediary candidate poses based on the pose objective function to compute the estimated pose of the client device.