Selective image pyramid computation for motion blur mitigation in visual-inertial tracking

1. A method for selective motion blur mitigation in a visual tracking system comprising:

accessing a first image generated by an optical sensor of the visual tracking system;

identifying camera operating parameters of the optical sensor during the optical sensor generating the first image;

determining a motion of the optical sensor during the optical sensor generating the first image by accessing VIO data from a VIO system of the visual tracking system, the VIO data comprising an estimated angular velocity of the optical sensor, an estimated linear velocity of the optical sensor, and locations of feature points in the first image;

determining a motion blur level of the first image based on the camera operating parameters of the optical sensor and the motion of the optical sensor, wherein the motion blur level in different areas of the first image is based on at least one of the estimated angular velocity of the optical sensor, the estimated linear velocity of the optical sensor, or 3D locations of feature points in corresponding different areas of the first image; and

determining whether to downscale the first image using a pyramid computation algorithm based on the motion blur level.

2. The method of claim 1 , wherein determining the motion of the optical sensor comprises:

retrieving inertial sensor data from an inertial sensor of the visual tracking system, the inertial sensor data corresponding to the first image; and

determining an angular velocity of the visual tracking system based on the inertial sensor data,

wherein the motion blur level is based on the camera operating parameters and the angular velocity of the visual tracking system without analyzing a content of the first image.

3. The method of claim 1 ,

wherein the motion blur level is based on the camera operating parameters and the VIO data without analyzing a content of the first image.

4. The method of claim 1 , wherein the camera operating parameters comprise a combination of an exposure time of the optical sensor, a field of view of the optical sensor, an ISO value of the optical sensor, and an image resolution.

5. The method of claim 1 , further comprising:

determining that the motion blur level of the first image exceeds a motion blur threshold;

in response to detecting that the motion blur level of the first image exceeds the motion blur threshold, applying the pyramid computation algorithm to the first image to generate a downscaled version of the first image; and

identifying a feature in the downscaled version of the first image.

6. The method of claim 1 , further comprising:

detecting that the motion blur level of the first image is within a motion blur threshold; and

in response to detecting that the motion blur level of the first image is within the motion blur threshold, identifying a feature in the first image.

7. The method of claim 1 , wherein determining whether to downscale the first image further comprises:

estimating a likelihood of motion blur of a second image based on the camera operating parameters and the motion of the visual tracking system prior to the optical sensor generating the second image, the second image following the first image.

8. The method of claim 7 , further comprising:

detecting that the likelihood of motion blur of the second image exceeds a motion blur threshold;

in response to detecting that the likelihood of motion blur level of the second image exceeds the motion blur threshold, applying the pyramid computation algorithm to the first image to generate a downscaled version of the first image; and

identifying a feature in the downscaled version of the first image.

9. The method of claim 7 , further comprising:

detecting that the likelihood of motion blur of the second image is within a motion blur threshold; and

in response to detecting that the likelihood of motion blur of the second image is within the motion blur threshold, identifying a feature in the first image.

10. The method of claim 1 , further comprising:

matching feature points between a downscaled version of the first image and a downscaled version of a second image; and

identifying a pose of the visual tracking system based on the matched feature points.

11. A computing apparatus comprising:

a processor; and

a memory storing instructions that, when executed by the processor, configure the apparatus to:

access a first image generated by an optical sensor of a visual tracking system;

identify camera operating parameters of the optical sensor during the optical sensor generating the first image;

determine a motion of the optical sensor during the optical sensor generating the first image by accessing VIO data from a VIO system of the visual tracking system, the VIO data comprising an estimated angular velocity of the optical sensor, an estimated linear velocity of the optical sensor, and locations of feature points in the first image;

determine a motion blur level of the first image based on the camera operating parameters of the optical sensor and the motion of the optical sensor, wherein the motion blur level in different areas of the first image is based on at least one of the estimated angular velocity of the optical sensor, the estimated linear velocity of the optical sensor, or 3D locations of feature points in corresponding different areas of the first image; and

determine whether to downscale the first image using a pyramid computation algorithm based on the motion blur level.

12. The computing apparatus of claim 11 , wherein determining the motion of the optical sensor comprises:

retrieve inertial sensor data from an inertial sensor of the visual tracking system, the inertial sensor data corresponding to the first image; and

determine an angular velocity of the visual tracking system based on the inertial sensor data,

wherein the motion blur level is based on the camera operate parameters and the angular velocity of the visual tracking system without analyzing a content of the first image.

13. The computing apparatus of claim 11 ,

wherein the motion blur level is based on the camera operating parameters and the VIO data without analyzing a content of the first image.

14. The computing apparatus of claim 11 , wherein the camera operate parameters comprise a combination of an exposure time of the optical sensor, a field of view of the optical sensor, an ISO value of the optical sensor, and an image resolution.

15. The computing apparatus of claim 11 , wherein the instructions further configure the apparatus to:

determine that the motion blur level of the first image exceeds a motion blur threshold;

in response to detecting that the motion blur level of the first image exceeds the motion blur threshold, apply the pyramid computation algorithm to the first image to generate a downscaled version of the first image; and

identify a feature in the downscaled version of the first image.

16. The computing apparatus of claim 11 , wherein the instructions further configure the apparatus to:

detect that the motion blur level of the first image is within a motion blur threshold; and

in response to detecting that the motion blur level of the first image is within the motion blur threshold, identify a feature in the first image.

17. The computing apparatus of claim 11 , wherein determining whether to downscale the first image further comprises:

estimate a likelihood of motion blur of a second image based on the camera operating parameters and the motion of the visual tracking system prior to the optical sensor generating the second image, the second image following the first image.

18. The computing apparatus of claim 17 , wherein the instructions further configure the apparatus to:

detect that the likelihood of motion blur of the second image exceeds a motion blur threshold;

in response to detecting that the likelihood of motion blur level of the second image exceeds the motion blur threshold, apply the pyramid computation algorithm to the first image to generate a downscaled version of the first image; and

identify a feature in the downscaled version of the first image.

19. The computing apparatus of claim 17 , wherein the instructions further configure the apparatus to:

detect that the likelihood of motion blur of the second image is within a motion blur threshold; and

in response to detecting that the likelihood of motion blur of the second image is within the motion blur threshold, identify a feature in the first image.

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:

access a first image generated by an optical sensor of a visual tracking system;

identify camera operating parameters of the optical sensor during the optical sensor generating the first image by accessing VIO data from a VIO system of the visual tracking system, the VIO data comprising an estimated angular velocity of the optical sensor, an estimated linear velocity of the optical sensor, and locations of feature points in the first image;

determine a motion of the optical sensor during the optical sensor generating the first image;

determine a motion blur level of the first image based on the camera operating parameters of the optical sensor and the motion of the optical sensor, wherein the motion blur level in different areas of the first image is based on at least one of the estimated angular velocity of the optical sensor, the estimated linear velocity of the optical sensor, or 3D locations of feature points in corresponding different areas of the first image; and

determine whether to downscale the first image using a pyramid computation algorithm based on the motion blur level.