User analytics using a mobile device camera and associated systems and methods

1. A computer-implemented method for performing location and movement determination in a three-dimensional environment using a mobile computing device having a camera, comprising:

capturing one or more images of a user using the camera on the mobile computing device;

determining the user from the images using a machine learning algorithm;

determining a pose associated with the user using a machine vision algorithm;

determining a depth of the user with respect to the camera based on the pose and an input height of the user using a binary search process; and

determining the location of the user in the environment based on the pose and the depth.

2. The computer-implemented method of claim 1 , further comprising:

determining a movement associated with the user based on the pose.

3. The computer-implemented method of claim 1 , further comprising:

determining a direction of gravity using a sensor associated with the mobile computing device;

determining the user's feet location in the three-dimensional environment; and

determining, based on the user's feet location, a distance between the camera and the user's feet location.

4. The computer-implemented method of claim 3 , further comprising:

determining, based on the distance, a ground plane in the camera's coordinate system.

5. The computer-implemented method of claim 1 , further comprising:

determining that a ground is blocked from a view of the camera;

determining a first pose size of the user from a first user pose and determining a second pose size of the user from a second user pose; and

determining the depth based on one or more of the camera's center, a distance to an imaging plane, the input height, the first pose size, and the second pose size.

6. The computer-implemented method of claim 5 , further comprising:

determining the first pose size based on a pixel length of pose limbs associated with the first user pose.

7. The computer-implemented method of claim 1 , wherein the pose comprises noisy pose data, and the computer-implemented method further comprises:

applying a filter to the noisy pose data; and

determining a second location of the user based on the filtered noisy pose data, wherein the second location has a greater accuracy than the location.

8. A non-transitory storage medium for performing location and movement determination in a three-dimensional environment using a mobile computing device having a camera, the storage medium comprising machine-readable program code that cause a processor to:

capture one or more images of a user using the camera on the mobile computing device;

determine the user from the images using a machine learning algorithm;

determine a pose associated with the user using a machine vision algorithm;

determine a depth of the user with respect to the camera based on the pose and an input height of the user using a binary search process; and

determine the location of the user in the environment based on the pose and the depth.

9. The non-transitory storage medium of claim 8 , further comprising program code to:

determine a movement associated with the user based on the pose.

10. The non-transitory storage medium of claim 8 , further comprising program code to:

determine a direction of gravity using a sensor associated with the mobile computing device;

determine the user's feet location in the three-dimensional environment; and

determine, based on the user's feet location, a distance between the camera and the user's feet location.

11. The non-transitory storage medium of claim 10 , further comprising program code to:

determine, based on the distance, a ground plane in the camera's coordinate system.

12. The non-transitory storage medium of claim 8 , further comprising program code to:

determine that a ground is blocked from a view of the camera;

determine a first pose size of the user from a first user pose and determining a second pose size of the user from a second user pose; and

determine the depth based on one or more of the camera's center, a distance to an imaging plane, the input height, the first pose size, and the second pose size.

13. The non-transitory storage medium of claim 12 , further comprising program code to:

determine the first pose size based on a pixel length of pose limbs associated with the first user pose.

14. The non-transitory storage medium of claim 8 , wherein the pose comprises noisy pose data, and further comprising program code to:

apply a filter to the noisy pose data; and

determine a second location of the user based on the filtered noisy pose data, wherein the second location has a greater accuracy than the location.

15. A mobile computing device for performing location and movement determination in a three-dimensional environment, comprising:

a camera device;

a processor; and

a non-transitory memory storing program code thereon, the program code executable by the processor to:

capture one or more images of a user using the camera on the mobile computing device;

determine the user from the images using a machine learning algorithm;

determine a pose associated with the user using a machine vision algorithm;

determine a depth of the user with respect to the camera based on the pose and an input height of the user using a binary search process; and

determine the location of the user in the environment based on the pose and the depth.

16. The mobile computing device of claim 15 , further comprising program code to:

determine a movement associated with the user based on the pose.

17. The mobile computing device of claim 15 , further comprising program code to:

determine a direction of gravity using a sensor associated with the mobile computing device;

determine the user's feet location in the three-dimensional environment; and

determine, based on the user's feet location, a distance between the camera and the user's feet location.

18. The mobile computing device of claim 17 , further comprising program code to:

determine, based on the distance, a ground plane in the camera's coordinate system.

19. The mobile computing device of claim 15 , further comprising program code to:

determine that a ground is blocked from a view of the camera;

determine a first pose size of the user from a first user pose and determining a second pose size of the user from a second user pose; and

determine the depth based on one or more of the camera's center, a distance to an imaging plane, the input height, the first pose size, and the second pose size.

20. The mobile computing device of claim 19 , further comprising program code to:

determine the first pose size based on a pixel length of pose limbs associated with the first user pose.