Non-overlapped stereo imaging for virtual reality headset tracking

1. A system comprising:

a virtual reality headset;

a first camera and a second camera on the virtual reality headset, each camera having a field of view and capturing image data of an environment of the virtual reality headset, wherein a portion of the fields of view of the first and second cameras overlap and a portion of the fields of view do not overlap; and

a processor receiving the image data from the first and second cameras and configured to:

identify a first observation of a position of the virtual reality headset in the environment and positions of a plurality of features in the environment based on the image data captured by the first camera;

identify a second observation of the position of the virtual reality headset in the environment and the positions of the plurality of features in the environment based on the image data captured by the second camera;

determine, based on features appearing in the overlapping portion of the fields of view, a scale for objects in the environment;

determine a size of an object in the environment based on features appearing in the non-overlapping portion of the fields of view and further based on the scale; and

generate a three-dimensional model of the environment, the three-dimensional model comprising a representation of the object.

2. The system of claim 1 , wherein the virtual reality headset comprises an electronic display configured to display media to a user, and wherein the processor is further configured to:

display media to the user by the electronic display based at least in part on the model of the environment.

3. The system of claim 2 , wherein displaying the media comprises:

displaying one or more virtual objects positioned in the environment based on the model of the environment.

4. The system of claim 2 , wherein displaying the media comprises:

detecting changes in positions of one or more features in the environment; and

modifying the displayed media responsive to the detected changes.

5. The system of claim 1 , wherein the processor is further configured to identify an initial position of the virtual reality headset in the environment by identifying distances between a reference point of the headset at the initial position and each of the identified features.

6. The system of claim 5 , further comprising:

one or more motion sensors on the virtual reality headset, each motion sensor generating motion data corresponding to movement of the virtual reality headset;

wherein the processor is further configured to, after the virtual reality headset has been moved from the initial position to a new position in the environment:

generate a first estimate of the new position based on the motion data;

generate a second estimate of the new position based on observations of the features in image data captured by the first and second cameras;

determine a difference between the second estimate and the first estimate; and

identify the new position of the virtual reality headset based on the first estimate, the second estimate, and the determined difference.

7. The system of claim 6 , wherein generating the second estimate comprises correlating features observed in image data captured by the first camera with features observed in image data captured by the second camera.

8. The system of claim 6 , wherein the virtual reality headset comprises an electronic display configured to display media to a user, and wherein the processor is further configured to display media to the user based at least in part on the motion data.

9. The system of claim 5 , wherein the processor is further configured to:

identify one or more additional features in the environment based on the image data captured by the first camera and the image data captured by the second camera at a new position of the virtual reality headset.

10. A method comprising:

receiving image data of an environment of a virtual reality headset, the image data captured by a first camera and a second camera coupled to the virtual reality headset and each having a field of view, wherein a portion of the fields of view of the first and second cameras overlap and a portion of the fields of view do not overlap;

identifying a first observation of a position of the virtual reality headset in the environment and positions of a plurality of features in the environment based on the image data captured by the first camera;

identifying a second observation of the position of the virtual reality headset in the environment and the positions of the plurality of features in the environment based on the image data captured by the second camera;

determining, based on features appearing in the overlapping portion of the fields of view, a scale for objects in the environment;

determining a size of an object in the environment based on features appearing in the non-overlapping portion of the fields of view and further based on the scale; and

generating a three-dimensional model of the environment, the three-dimensional model comprising a representation of the object.

11. The method of claim 10 , wherein the virtual reality headset comprises an electronic display configured to display media to a user, and wherein the method further comprises:

displaying media to the user by the electronic display based at least in part on the model of the environment.

12. The method of claim 11 , wherein displaying the media comprises:

displaying one or more virtual objects positioned in the environment based on the model of the environment.

13. The method of claim 11 , wherein displaying the media comprises:

detecting changes in positions of one or more features in the environment; and

modifying the displayed media responsive to the detected changes.

14. The method of claim 10 , further comprising:

identifying an initial position of the virtual reality headset in the environment by identifying distances between a reference point of the headset at the initial position and each of the identified features.

15. The method of claim 14 , wherein the virtual reality headset further comprises one or more motion sensors each generating motion data corresponding to movement of the virtual reality headset, the method further comprising, after the virtual reality headset has been moved from the initial position to a new position in the environment:

generating a first estimate of the new position based on the motion data;

generating a second estimate of the new position based on observations of the features in image data captured by the first and second cameras; and

determining a difference between the second estimate and the first estimate.

16. The method of claim 15 , wherein generating the second estimate comprises correlating features observed in image data captured by the first camera with features observed in image data captured by the second camera.

17. The method of claim 15 , wherein the virtual reality headset comprises an electronic display configured to display media to a user, and wherein the method further comprises displaying media to the user based at least in part on the motion data.

18. The method of claim 14 , further comprising:

identifying one or more additional features in the environment based on the image data captured by the first camera and the image data captured by the second camera at a new position of the virtual reality headset.