Capturing and aligning panoramic image and depth data
This application generally relates to capturing and aligning panoramic image and depth data. In one embodiment, a device is provided that comprises a housing and a plurality of cameras configured to capture two-dimensional images, wherein the cameras are arranged at different positions on the housing and have different azimuth orientations relative to a center point such that the cameras have a collective field-of-view spanning up to 360° horizontally. The device further comprises a plurality of depth detection components configured to capture depth data, wherein the depth detection components are arranged at different positions on the housing and have different azimuth orientations relative to the center point such that the depth detection components have the collective field-of-view spanning up to 360° horizontally.
1. A device comprising:
a housing including:
at least one camera having a fisheye camera lens configured to capture 2D image data of an environment from a fixed location;
at least one depth sensor device including at least one light imaging detection and ranging (LiDAR) device, the at least one depth sensor device being configured to capture 3D depth data of the environment;
a horizontal rotatable mount configured to enable the fisheye camera lens of the at least one camera to move in a horizontal x axis relative to the device, the at least one camera being capable of capturing a plurality of images with mutually overlapping fields of view at different viewpoints;
at least one processor configured to map the 2D image data from the at least one camera and the 3D depth data from the at least one depth sensor device to a common spatial 3D coordinate space based on known capture positions and orientations of the at least one camera and the at least one depth sensor device to facilitate associating 3D coordinates with respective visual features included in the 2D image data relative to the common spatial 3D coordinate space; and
a 3D model generation component configured to generate a 3D model of the environment from the 2D image data from the at least one camera and 3D depth data from the at least one depth sensor.
2. The device of claim 1 , further including a vertical rotatable mount configured to enable the fisheye camera lens of the at least one camera to move in a vertical y axis relative to the device.
3. The device of claim 2 , wherein the horizontal rotatable mount and the horizontal rotatable mount includes at least one motor configured to move at least the fisheye camera lens.
4. The device of claim 1 , wherein the fisheye camera lens provides a field of a view from 100 degrees to 195 degrees.
5. The device of claim 1 , wherein the at least one processor is further configured to merge and align a plurality of 2D images captured by the at least one camera to generate a panoramic 2D image of the environment.
6. The device of claim 5 , wherein the at least one processor is further configured to merge and align the 3D depth data based on information from the at least one sensor device to generate a 3D image of the environment.
7. The device of claim 1 , wherein the at least one camera is a color video camera capable of capturing color video of the environment.
8. The device of claim 1 , wherein the at least one processor is further configured to determine each capture location relative to each other using positional tracking.
9. The device of claim 8 , wherein the positional tracking includes inertial position tracking.
10. The device of claim 8 , wherein the positional tracking includes utilizing simultaneous localization and mapping (SLAM) analysis.
11. A method comprising:
capturing, by at least one camera in a housing, 2D image data of an environment from a fixed location, the at least one camera having a fisheye camera lens;
capturing, by at least one depth sensor device in the housing, 3D depth data of the environment, the at least one depth sensor device including at least one light imaging detection and ranging (LiDAR) device;
moving, by a horizontal rotatable mount, at least the fisheye camera lens in a horizontal x axis relative to the device, the at least one camera being capable of capturing a plurality of images with mutually overlapping fields of view at different viewpoints;
mapping, by at least one processor in the housing, the 2D image data from the at least one camera and the 3D depth data from the at least one depth sensor device to a common spatial 3D coordinate space based on known capture positions and orientations of the at least one camera and the at least one depth sensor device to facilitate associating 3D coordinates with respective visual features included in the 2D image data relative to the common spatial 3D coordinate space; and
generating a 3D model of the environment from the 2D image data from the at least one camera and 3D depth data from the at least one depth sensor.
12. The method of claim 11 , further comprising moving, by a vertical rotatable mount, the fisheye camera lens of the at least one camera in a vertical y axis relative to the device.
13. The method of claim 12 , wherein the horizontal rotatable mount and the horizontal rotatable mount includes at least one motor configured to move at least the fisheye camera lens.
14. The method of claim 11 , wherein the fisheye camera lens provides a field of a view from 100 degrees to 195 degrees.
15. The method of claim 11 , further comprising merging and aligning, by the at least one processor, a plurality of 2D images captured by the at least one camera to generate a panoramic 2D image of the environment.
16. The method of claim 15 , further comprising merging and aligning, by the at least one processor, the 3D depth data based on information from the at least one sensor device to generate a 3D image of the environment.
17. The method of claim 11 , wherein the at least one camera is a color video camera capable of capturing color video of the environment.
18. The method of claim 11 , further comprising determining, by the at least one processor, each capture location relative to each other using positional tracking.
19. The method of claim 18 , wherein using the positional tracking includes inertial position tracking.
20. The method of claim 18 , wherein using the positional tracking includes utilizing simultaneous localization and mapping (SLAM) analysis.
21. A nontransitory computer readable medium comprising instructions executable by a processor to perform a method, the method comprising:
capturing, by at least one camera in a housing, 2D image data of an environment from a fixed location, the at least one camera having a fisheye camera lens;
capturing, by at least one depth sensor device in the housing, 3D depth data of the environment, the at least one depth sensor device including at least one light imaging detection and ranging (LiDAR) device;
moving, by a horizontal rotatable mount, at least the fisheye camera lens in a horizontal x axis relative to the device, the at least one camera being capable of capturing a plurality of images with mutually overlapping fields of view at different viewpoints;
applying, by at least one processor in the housing, the 2D image data from the at least one camera and the 3D depth data from the at least one depth sensor device to a common spatial 3D coordinate space based on known capture positions and orientations of the at least one camera and the at least one depth sensor device to facilitate associating 3D coordinates with respective visual features included in the 2D image data relative to the common spatial 3D coordinate space; and
generating a 3D model of the environment from the 2D image data from the at least one camera and 3D depth data from the at least one depth sensor.