System and methods for improved aerial mapping with aerial vehicles
A method for image generation, preferably including: generating a set of mission parameters for a UAV mission of the UAV associated with aerial scanning of a region of interest; controlling the UAV to perform the mission; generating an image subassembly corresponding to the mission; and/or rendering the image subassembly at a display.
1. A computer-implemented method comprising:
receiving, by one or more processors, first frames of a region of interest captured by a camera of an unmanned aerial vehicle (UAV);
determining, by the one or more processors, second frames within a temporal window of the first frames, corresponding to a limited number of the first frames which are most recently captured or processed;
determining, by the one or more processors, third frames within a spatial window of the first frames corresponding to a limited number of the first frames with overlap greater than a first threshold or a number of matched features greater than a second threshold;
performing, by the one or more processors, a bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using; frames included within both the temporal window and the spatial window; and
generating, by the one or more processors, a subassembly of frames, based on performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames included within both the temporal window and the spatial window.
2. The computer-implemented method of claim 1 , wherein the camera extrinsic parameters include a position of the camera and an orientation of the camera.
3. The computer-implemented method of claim 1 , further comprising:
determining a feature in the region of interest; and
determining a physical position of the feature in the region of interest,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera to minimize a reprojection error associated with the physical position of the feature.
4. The computer-implemented method of claim 1 , further comprising:
fixing camera pose parameters at a specific value,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames, based on fixing the camera pose parameters at the specific value.
5. The computer-implemented method of claim 1 , further comprising:
constraining camera pose parameters within a specific range of values,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames, based on constraining the camera pose parameters within the specific range of values.
6. The computer-implemented method of claim 1 , further comprising:
providing the subassembly of frames to an electronic device of a user to render the region of interest in near-real time at a display of the electronic device.
7. A device comprising:
a memory configured to store instructions; and
a processor configured to execute the instructions to perform operations comprising:
receiving first frames of a region of interest captured by a camera of an unmanned aerial vehicle (UAV);
determining second frames within a temporal window of the first frames, corresponding to a limited number of the first frames which are most recently captured or processed
determining, third frames within a spatial window of the first frames corresponding to a limited number of the first frames with overlap greater than a first threshold or a number of matched features greater than a second threshold;
performing a bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using frames included within both the temporal window and the spatial window; and
generating a subassembly of frames, based on performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames included within both the temporal window and the spatial window.
8. The device of claim 7 , wherein the camera extrinsic parameters include a position of the camera and an orientation of the camera.
9. The device of claim 7 , wherein the operations further comprise:
determining a feature in the region of interest; and
determining a physical position of the feature in the region of interest, and
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera to minimize a reprojection error associated with the physical position of the feature.
10. The device of claim 7 , wherein the operations further comprise:
fixing camera pose parameters at a specific value,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames, based on fixing the camera pose parameters at the specific value.
11. The device of claim 7 , wherein the operations further comprise:
constraining camera pose parameters within a specific range of values,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames, based on constraining the camera pose parameters within the specific range of values.
12. The device of claim 7 , wherein the operations further comprise:
providing the subassembly of frames to an electronic device of a user to render the region of interest in near-real time at a display of the electronic device.
13. A non-transitory computer-readable medium configured to store instructions that, when executed by a processor, perform operations comprising:
receiving first frames of a region of interest captured by a camera of an unmanned aerial vehicle (UAV);
determining second frames within a temporal window of the first frames, corresponding to a limited number of the first frames which are most recently captured or processed;
determining third frames within a spatial window of the first frames corresponding to a limited number of the first frames with overlap greater than a first threshold or a number of matched features greater than a second threshold;
performing a bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using frames included within both the temporal window and the spatial window; and
generating a subassembly of frames, based on performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames included within both the temporal window and the spatial window.
14. The non-transitory computer-readable medium of claim 13 , wherein the camera extrinsic parameters include a position of the camera and an orientation of the camera.
15. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:
determining a feature in the region of interest; and
determining a physical position of the feature in the region of interest, and
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera to minimize a reprojection error associated with the physical position of the feature.
16. The non-transitory computer-readable medium of 13, wherein the operations further comprise:
fixing camera pose parameters at a specific value,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames, based on fixing the camera pose parameters at the specific value.
17. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:
constraining camera pose parameters within a specific range of values,
wherein the performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames comprises performing the bundle adjustment operation including optimizing over camera extrinsic parameters of the camera using the frames, based on constraining the camera pose parameters within the specific range of values.