System and method for calibration of machine vision cameras along at least three discrete planes
This invention provides a system and method for generating camera calibrations for a vision system camera along three discrete planes in a 3D volume space that uses at least two (e.g. parallel) object planes at different known heights. For any third (e.g. parallel) plane of a specified height, the system and method then automatically generates calibration data for the camera by interpolating/extrapolating from the first two calibrations. This alleviates the need to set the calibration object at more than two heights, speeding the calibration process and simplifying the user's calibration setup, and also allowing interpolation/extrapolation to heights that are space-constrained, and not readily accessible by a calibration object. The calibration plate can be calibrated at each height using a full 2D hand-eye calibration, or using a hand-eye calibration at the first height and then at a second height with translation to a known position along the height (e.g. Z) direction.
1. A system for calibrating a vision system camera along at least three discrete planes comprising:
a vision system camera assembly having a field of view within a volume space;
at least one calibration object having calibration features;
a calibration process that, with acquired images of the calibration object, performs (a) a first hand-eye calibration using the calibration object at a first position within a first plane of a first height of the volume space, and (b) a second hand-eye calibration using the calibration object at a second position within a second plane of a second height of the volume space that is separated from the first plane such that the first position within the first plane is distinct relative to the second position within the second plane; and
an interpolation/extrapolation process that is associated with the calibration process that receives calibration data from the first hand-eye calibration and the second hand-eye calibration and therewith generates three-dimensional (3D) calibration data for within the volume space.
2. The system as set forth in claim 1 , wherein the first plane and the second plane are parallel.
3. The system as set forth in claim 1 , wherein the calibration object in the second position is at least one of: translated within the second plane relative to the first position within the first plane; or rotated within the second plane relative to the first position within the first plane.
4. The system as set forth in claim 1 , wherein a position of interest lies on a third plane that is tilted relative to at least one of the first plane or the second plane.
5. The system as set forth in claim 1 , further comprising a ray identification process that computes a plurality of 3D rays corresponding to a plurality of pixels of the vision system camera.
6. The system as set forth in claim 5 , wherein each of the plurality of pixels of the vision system camera corresponds to a respective 3D ray of the plurality of 3D rays.
7. The system as set forth in claim 5 , wherein at least one respective 3D ray intersects with the first plane at a first (X,Y) position and the second plane at a second (X,Y) position.
8. A system for calibrating a vision system camera along at least three discrete planes comprising:
a vision system camera assembly having a field of view within a volume space;
at least one calibration object having calibration features;
a calibration process that, with acquired images of the calibration object, performs (a) a first hand-eye calibration using the calibration object at a first position within a first plane of a first height of the volume space, and (b) a second hand-eye calibration using the calibration object at a second position within a second plane of a second height of the volume space that is separated from the first plane such that the first position within the first plane is distinct relative to the second position within the second plane; and
an interpolation/extrapolation process that is associated with the calibration process that receives calibration data from the first hand-eye calibration and the second hand-eye calibration and therewith generates three-dimensional (3D) calibration data for within the volume space, wherein the interpolation/extrapolation process defines a linear interpolation/extrapolation process that identifies a linear relationship between the first (X,Y) position, the second (X,Y) position, and a position of interest.
9. The system as set forth in claim 8 , wherein the linear interpolation/extrapolation process generates the calibration data for the position of interest and for a plurality of interpolated heights.
10. The system as set forth in claim 8 , wherein the linear interpolation/extrapolation process generates the calibration data for the position of interest during runtime.
11. A system for calibrating a vision system camera along at least three discrete planes comprising:
a vision system camera assembly having a field of view within a volume space;
at least one calibration object having calibration features;
a calibration process that, with acquired images of the calibration object, performs (a) a first hand-eye calibration using the calibration object at a first position within a first plane of a first height of the volume space, and (b) a second hand-eye calibration using the calibration object at a second position within a second plane of a second height of the volume space that is separated from the first plane such that the first position within the first plane is distinct relative to the second position within the second plane; and
an interpolation/extrapolation process that is associated with the calibration process that receives calibration data from the first hand-eye calibration and the second hand-eye calibration and therewith generates calibration data for a height of interest.
12. The system as set forth in claim 11 , wherein the calibration data for the height of interest comprises 3D calibration data.
13. The system as set forth in claim 11 , wherein the first plane and the second plane are parallel.
14. The system as set forth in claim 11 , wherein the calibration object in the second position is at least one of: translated within the second plane relative to the first position within the first plane; or rotated within the second plane relative to the first position within the first plane.
15. The system as set forth in claim 11 , wherein the height of interest lies on a third plane that is tilted relative to at least one of the first plane or the second plane.
16. The system as set forth in claim 11 , further comprising a ray identification process that computes a plurality of 3D rays corresponding to a plurality of pixels of the vision system camera.
17. The system as set forth in claim 16 , wherein each of the plurality of pixels of the vision system camera corresponds to a respective 3D ray of the plurality of 3D rays.
18. The system as set forth in claim 16 , wherein at least one respective 3D ray intersects with the first plane at a first (X,Y) position and the second plane at a second (X,Y) position.
19. A system for calibrating a vision system camera along at least three discrete planes comprising:
a vision system camera assembly having a field of view within a volume space;
at least one calibration object having calibration features;
a calibration process that, with acquired images of the calibration object, performs (a) a first hand-eye calibration using the calibration object at a first position within a first plane of a first height of the volume space, and (b) a second hand-eye calibration using the calibration object at a second position within a second plane of a second height of the volume space that is separated from the first plane such that the first position within the first plane is distinct relative to the second position within the second plane; and
an interpolation/extrapolation process that is associated with the calibration process that receives calibration data from the first hand-eye calibration and the second hand-eye calibration and therewith generates calibration data for a height of interest, wherein the interpolation/extrapolation process defines a linear interpolation/extrapolation process that identifies a linear relationship between the first (X,Y) position, the second (X,Y) position, and the height of interest; and
a ray identification process that computes a plurality of 3D rays corresponding to a plurality of pixels of the vision system camera, wherein at least one respective 3D ray intersects with the first plane at a first (X,Y) position and the second plane at a second (X,Y) position.
20. The system as set forth in claim 19 , wherein the linear interpolation/extrapolation process generates the calibration data for the height of interest and for a plurality of interpolated heights.
21. The system as set forth in claim 19 , wherein the linear interpolation/extrapolation process generates the calibration data for the height of interest during runtime.