Calibration of a surround view camera system
A method for automatic generation of calibration parameters for a surround view (SV) camera system is provided that includes capturing a video stream from each camera comprised in the SV camera system, wherein each video stream captures two calibration charts in a field of view of the camera generating the video stream; displaying the video streams in a calibration screen on a display device coupled to the SV camera system, wherein a bounding box is overlaid on each calibration chart, detecting feature points of the calibration charts, displaying the video streams in the calibration screen with the bounding box overlaid on each calibration chart and detected features points overlaid on respective calibration charts, computing calibration parameters based on the feature points and platform dependent parameters comprising data regarding size and placement of the calibration charts, and storing the calibration parameters in the SV camera system.
1. A method, comprising:
capturing, using a set of cameras of a camera system, images of a set of charts;
overlaying, using the camera system, a respective bounding box on each representation of the set of charts in the images;
searching, using the camera system, within the respective bounding box of each representation of the set of charts to identify feature points for the representation of the set of charts;
determining, using the camera system, a set of calibration matrices for each of the set of cameras based on the feature points;
determining, using the camera system, calibration parameters for each of the set of cameras based on the set of calibration matrices; and
calibrating, using the camera system, each of the set of cameras based on the calibration parameters.
2. The method of claim 1 , wherein each of the images captures two of the set of charts.
3. The method of claim 1 , wherein each of the set of charts is captured by two of the set of cameras arranged adjacently to each other.
4. The method of claim 1 , further comprising:
displaying, on a screen, the feature points in the corresponding image of each representation of the set of charts with at least a portion of the respective bounding box.
5. The method of claim 1 , further comprising:
storing the set of calibration parameters for each of the set of cameras to a storage device.
6. The method of claim 1 , wherein each representation of the set of charts is aligned with respect to the respective bounding box corresponding to the chart.
7. The method of claim 6 , wherein each representation of the set of charts is aligned with respect to a center of the respective bounding box.
8. The method of claim 1 , wherein each of the set of cameras is associated with a set of intrinsic parameters that comprises at least one of: a lens focal length or a lens distortion model of the camera.
9. The method of claim 8 , further comprising:
determining a mapping lookup table for each of the set of cameras based on the set of calibration matrices and the intrinsic parameters, wherein the mapping lookup table maps a location from a 3D view to a 2D view.
10. The method of claim 1 , wherein the set of calibration matrices for each of the set of cameras comprises a rotation matrix and a translation matrix.
11. The method of claim 1 , wherein each of the set of charts has a square shape, and the feature points corresponds to corners of the charts.
12. A camera system, comprising:
a set of cameras configured to capture images of a set of charts;
a memory storing program instructions; and
a processor configured to execute the program instructions to:
receive the images of the set of charts captured by the set of cameras;
overlay a respective bounding box on each representation of the set of charts in the images;
search within the respective bounding box of each representation of the set of charts to identify feature points for the representation of the set of charts;
determine a set of calibration matrices for each of a set of cameras of the camera system based on the feature points;
determine calibration parameters for each of the set of cameras based on the set of calibration matrices; and
calibrate each of the set of cameras based on the calibration parameters.
13. The camera system of claim 12 , wherein each of the images captures two of the set of charts.
14. The camera system of claim 12 , wherein each of the set of charts is captured by two of the set of cameras arranged adjacently to each other.
15. The camera system of claim 12 , wherein the processor is configured to execute the program instructions to:
cause the feature points in the corresponding image of each representation of the set of charts with at least a portion of the respective bounding box to be displayed on a screen.
16. The camera system of claim 12 , wherein each representation of the set of charts is aligned with respect to the respective bounding box corresponding to the chart.
17. The camera system of claim 16 , wherein each representation of the set of charts is aligned with respect to a center of the respective bounding box.
18. The camera system of claim 12 , wherein each of the set of cameras is associated with a set of intrinsic parameters that comprises at least one of: a lens focal length or a lens distortion model of the camera.
19. The camera system of claim 18 , wherein the processor is configured to execute the program instructions to:
determine a mapping lookup table for each of the set of cameras based on the set of calibration matrices and the intrinsic parameters, wherein the mapping lookup table maps a location from a 3D view to a 2D view.
20. A system comprising:
a non-transitory computer readable memory storing program instructions; and
a processor coupled to the non-transitory computer readable memory and configured to execute the program instructions to:
receive a set of images associated with a set of cameras, wherein the set of images includes a representation of a chart;
overlay a bounding box on the representation of the chart in the set of images;
search within the bounding box to identify feature points for the representation of the chart; and
determine calibration parameters for each of the set of cameras based on the feature points.