Systems and methods for dynamic image processing and segmentation

1. A method for obtaining a plurality of frames of image data, the method comprising:

obtaining a first frame and a second frame of image data of a field of view from a camera sensor;

defining one or more regions of the field of view based on a degree of motion detected in a plurality of areas of the field of view using the first frame and the second frame of image data;

determining a frame rate for each of the one or more regions based on the degree of motion detected in the plurality of areas of the field of view; and

obtaining a plurality of partial frames of image data by obtaining image data of the one or more regions of the field of view according to the frame rate.

2. The method of claim 1 , wherein the first frame and the second frame are full frames of an entirety of the field of view, wherein obtaining the first frame of image data comprises obtaining two or more frames of image data, and defining the one or more regions of the field of view comprises:

comparing the two or more frames to each other to identify a plurality of areas of motion; and

defining a plurality regions, each region associated with a different one of the plurality of areas of motion.

3. The method of claim 2 , wherein the plurality of areas of motion comprise at least a first area and a second area, wherein an amount of motion present at the first area is greater than an amount of motion present at the second area.

4. The method of claim 1 , wherein obtaining the plurality of partial frames of the image data comprises one of:

operating the camera sensor to obtain the plurality of partial frames of image data according to at least one of the frame rate and the image capture resolution; or

operating the camera sensor to obtain a plurality of full frames at a full resolution and a maximum frame rate, and obtaining the plurality of partial frames of image data according to at least one of the frame rate and the image capture resolution based on the plurality of full frames using an image signal processor or a sensor readout circuit.

5. The method of claim 1 , wherein defining the one or more regions of the field of view further comprises:

performing depth estimation to identify at least a foreground and a background of an environment; and

defining a first region associated with the foreground and a second region associated with the background.

6. The method of claim 5 , wherein the frame rate for the first region is greater than the frame rate for the second region.

7. The method of claim 1 , wherein defining the one or more regions of the field of view comprises:

detecting one or more objects in the field of view based on the frame of image data; and

defining a region for each of the one or more objects in the field of view.

8. The method of claim 1 , further comprising:

obtaining sensor data indicating a direction and magnitude of motion of a user's head; and

defining the one or more regions at least partially based on at least one of the direction or magnitude of motion of the user's head.

9. The method of claim 1 , further comprising constructing one or more frames using the plurality of partial frames of image data.

10. A system comprising:

a head wearable display comprising a camera sensor, and at least one of an inertial measurement unit (IMU), a visual inertial odometry (VIO) sensor, or a depth sensor; and

processing circuitry configured to:

obtain a first frame of image data of a field of view from the camera sensor;

define one or more regions of the field of view using the first frame of image data based on feedback from the IMU, the VIO sensor, or the depth sensor;

determine at least one of a frame rate and an image capture resolution for each of the one or more regions based on the feedback from the IMU, the VIO sensor, or the depth sensor; and

operate the camera sensor to obtain a plurality of partial frames of image data by obtaining image data of the one or more regions of the field of view according to at least one of the frame rate and the image capture resolution.

11. The system of claim 10 , wherein the processing circuitry comprises both local processing circuitry positioned at the head wearable display, and remote processing circuitry positioned remotely from the head wearable display.

12. The system of claim 11 , wherein the remote processing circuitry is a processing circuitry of a user's personal computing device.

13. The system of claim 10 , wherein the head wearable display further comprises a battery, the battery configured to provide electrical power to any of the processing circuitry, the camera sensor, the IMU, or the VIO sensor, wherein defining the one or more regions, determining the at least one of the frame rate or the image capture resolution, and operating the camera sensor to obtain the plurality of partial frames reduces power consumption from the battery by a factor.

14. The system of claim 13 , wherein the factor is a function of a number of the one or more regions, frame rates of each of the one or more regions, resolutions of each of the one or more regions, a nominal frame rate, and a nominal resolution.

15. The system of claim 10 , further comprising at least one of a plurality of light emitting diodes (LEDs) or a speaker, wherein the processing circuitry is configured to:

track a relative position of one of the one or more regions relative to a periphery of the field of view of the camera sensor; and

operate at least one of the plurality of LEDs or the speaker in response to the one of the one or more regions approaching the periphery of the field of view of the camera sensor to inform the user regarding the periphery of the field of view of the camera sensor.

16. The system of claim 15 , wherein the plurality of LEDs are positioned along a frame of the head wearable display.

17. A method for obtaining a plurality of frames of image data, the method comprising:

obtaining spatial audio from a spatial audio sensor and feedback from at least one of an inertial measurement unit (IMU), a visual inertial odometry (VIO) sensor, or a depth sensor;

defining one or more regions of a field of view of a camera sensor based on the spatial audio and the feedback;

determining a frame rate for each of the one or more regions of the field of view of the camera sensor based on at least one of the spatial audio or the feedback; and

operating the camera sensor to obtain partial frames of each of the one or more regions according to the frame rate for each of the one or more regions.

18. The method of claim 17 , further comprising constructing one or more frames using the partial frames of image data.

19. The method of claim 17 , wherein the spatial audio sensor comprises an array of microphones.

20. The method of claim 17 , wherein at least one of the one or more regions are centered at a spatial audio source.