Machine vision system calibration

Abstract

Disclosed herein are systems and methods for machine vision. A machine vision system includes a motion rendering device, a first image sensor, and a second image sensor. The machine visions system includes a processor configured to run a computer program stored in memory that is configured to determine a first transformation that allows mapping between the first coordinate system associated with the motion rendering device and the second coordinate system associated with the first image sensor, and to determine a second transformation that allows mapping between the first coordinate system associated with the motion rendering device and the third coordinate system associated with the second image sensor.

1 .- 16 . (canceled) 
     
     
         17 . A system, comprising:
 a processor configured to run a computer program stored in memory that is configured to:
 receive, from a first image sensor, a first image of an object at a first pose of a motion rendering device, wherein the motion rendering device is associated with a first coordinate system and is configured to directly or indirectly carry the object, wherein the first image sensor is associated with a second coordinate system; 
 receive, from a second image sensor, a second image of the object at the first pose of the motion rendering device, wherein the second image sensor is associated with a third coordinate system; 
 access a first transformation that allows mapping between the first coordinate system associated with the motion rendering device and the second coordinate system associated with the first image sensor, wherein the first transformation was determined based on a first plurality of correspondences between known physical positions of a first plurality of features of a first calibration plate at a training pose of the motion rendering device and first positions of the first plurality of features detected in a first training image obtained by the first image sensor of the first calibration plate at the training pose of the motion rendering device; 
 access a second transformation that allows mapping between the first coordinate system associated with the motion rendering device and the third coordinate system associated with the second image sensor, wherein the second transformation was determined based on a second plurality of correspondences between known physical positions of a second plurality of features of a second calibration plate at the training pose of the motion rendering device and second positions of the second plurality of features detected in a second training image obtained by the second image sensor of the second calibration plate at the training pose of the motion rendering device; and 
 based on the first and second transformations, establish correspondences between features of the object found in the first and second images taken by the first and second image sensors and the first coordinate system. 
   
     
     
         18 . The system of  claim 17 , wherein the motion rendering device is configured to provide at least one of a translational movement and an in-plane rotational movement. 
     
     
         19 . The system of  claim 18 , wherein the computer program is operable to cause the processor to determine a motion correction transform that compensates for a systematic motion error associated with the motion rendering device. 
     
     
         20 . The system of  claim 17 , wherein the computer program is operable to cause the processor to re-calibrate the system after a first period of time, comprising re-determining:
 the first plurality of correspondences;   the second plurality of correspondences;   the first transformation; and   the second transformation.   
     
     
         21 . The system of  claim 20 , wherein re-calibrating the system comprises adjusting one or more pre-calibrated parameters. 
     
     
         22 . A system, comprising:
 a processor configured to run a computer program stored in memory that is configured to:
 receive, from a first image sensor, a first image of an object from a first pose of a motion rendering device, wherein the motion rendering device is associated with a first coordinate system and is configured to directly or indirectly carry the first image sensor and a second image sensor, wherein the first image sensor is associated with a second coordinate system; 
 receive, from the second image sensor, a second image of the object from the first pose of the motion rendering device, wherein the second image sensor is associated with a third coordinate system; 
 access a first transformation that allows mapping between the first coordinate system associated with the motion rendering device and the second coordinate system associated with the first image sensor, wherein the first transformation was determined based on a first plurality of correspondences between known physical positions of a first plurality of features of a first calibration plate from a training pose of the motion rendering device and first positions of the first plurality of features detected in a first training image obtained by the first image sensor of the first calibration plate from the training pose of the motion rendering device; 
 access a second transformation that allows mapping between the first coordinate system associated with the motion rendering device and the third coordinate system associated with the second image sensor, wherein the second transformation was determined based on a second plurality of correspondences between known physical positions of a second plurality of features of a second calibration plate from the training pose of the motion rendering device and second positions of the second plurality of features detected in a second training image obtained by the second image sensor of the second calibration plate from the training pose of the motion rendering device; and 
 based on the first and second transformations, establish correspondences between features of the object found in the first and second images taken by the first and second image sensors and the first coordinate system. 
   
     
     
         23 . The system of  claim 22 , wherein the motion rendering device is configured to provide at least one of a translational movement and an in-plane rotational movement 
     
     
         24 . The system of  claim 23 , wherein the computer program is operable to cause the processor to determine a motion correction transform that compensates for a systematic motion error associated with the motion rendering device. 
     
     
         25 . The system of  claim 22 , wherein the computer program is operable to cause the processor to re-calibrate the system after a first period of time, comprising re-determining:
 the first plurality of correspondences;   the second plurality of correspondences;   the first transformation; and   the second transformation.   
     
     
         26 . The system of  claim 25 , wherein re-calibrating the system comprises adjusting one or more pre-calibrated parameters. 
     
     
         27 . A system, comprising:
 a processor configured to run a computer program stored in memory that is configured to:
 receive, from a first image sensor, a first image of an object at a first pose of a motion rendering device, wherein the motion rendering device is associated with a first coordinate system and is configured to directly or indirectly carry the object, wherein the first image sensor is associated with a second coordinate system; 
 receive, from a second image sensor, a second image of the object at the first pose of the motion rendering device, wherein the second image sensor is associated with a third coordinate system; 
 access a first transformation that allows mapping between the first coordinate system associated with the motion rendering device and the second coordinate system associated with the first image sensor, wherein the first transformation was determined based on a first subset of a plurality of features of a training object detected in a first training image obtained by the first image sensor of the training object at a training pose of the motion rendering device; 
 access a second transformation that allows mapping between the first coordinate system associated with the motion rendering device and the third coordinate system associated with the second image sensor, wherein the second transformation was determined based on a second subset of the plurality of features of the training object detected in a second training image obtained by the second image sensor of the training object at the training pose of the motion rendering device; and 
 based on the first and second transformations, establish correspondences between features of the object found in the first and second images taken by the first and second image sensors and the first coordinate system. 
   
     
     
         28 . The system of  claim 27 , wherein the motion rendering device is configured to provide at least one of a translational movement and an in-plane rotational movement 
     
     
         29 . The system of  claim 28 , wherein the computer program is operable to cause the processor to determine a motion correction transform that compensates for a systematic motion error associated with the motion rendering device. 
     
     
         30 . The system of  claim 27 , wherein the computer program is operable to cause the processor to re-calibrate the system after a first period of time, comprising re-determining:
 the first subset of the plurality of features;   the second subset of the plurality of features;   the first transformation; and   the second transformation.   
     
     
         31 . The system of  claim 30 , wherein re-calibrating the system comprises adjusting one or more pre-calibrated parameters. 
     
     
         32 . A system, comprising:
 a processor configured to run a computer program stored in memory that is configured to:
 receive, from a first image sensor, a first image of an object from a first pose of a motion rendering device, wherein the motion rendering device is associated with a first coordinate system and is configured to directly or indirectly carry the first image sensor and a second image sensor, wherein the first image sensor is associated with a second coordinate system; 
 receive, from the second image sensor, a second image of the object from the first pose of the motion rendering device, wherein the second image sensor is associated with a third coordinate system; 
 access a first transformation that allows mapping between the first coordinate system associated with the motion rendering device and the second coordinate system associated with the first image sensor, wherein the first transformation was determined based on a first subset of a plurality of features of a training object detected in a first training image obtained by the first image sensor of the training object from a training pose of the motion rendering device; 
 access a second transformation that allows mapping between the first coordinate system associated with the motion rendering device and the third coordinate system associated with the second image sensor, wherein the second transformation was determined based on a second subset of the plurality of features of the training object detected in a second training image obtained by the second image sensor of the training object from the training pose of the motion rendering device; and 
 based on the first and second transformations, establish correspondences between features of the object found in the first and second images taken by the first and second image sensors and the first coordinate system. 
   
     
     
         33 . The system of  claim 32 , wherein the motion rendering device is configured to provide at least one of a translational movement and an in-plane rotational movement. 
     
     
         34 . The system of  claim 33 , wherein the computer program is operable to cause the processor to determine a motion correction transform that compensates for a systematic motion error associated with the motion rendering device. 
     
     
         35 . The system of  claim 32 , wherein the computer program is operable to cause the processor to re-calibrate the system after a first period of time, comprising re-determining:
 the first subset of the plurality of features;   the second subset of the plurality of features;   the first transformation; and   the second transformation.   
     
     
         36 . The system of  claim 35 , wherein re-calibrating the system comprises adjusting one or more pre-calibrated parameters.