Table Of Contents

Learn Binocular Stereo Calibration (G Dataflow)

Last Modified: June 25, 2019

Learns binocular stereo information.

This node takes the calibrated template images from the left and right cameras as input, and computes the calibration information required for binocular stereo vision. The calibration process computes the rotation matrix and translation vector between the two cameras and also computes the essential and fundamental matrices. During the learn process, this node will also compute the lookup tables required to rectify the left and right images and identifies the regions in the left and right images that overlap. This node assumes that both the calibrated templates have been learned from the same set of grid images or points. This node uses the reference points stored in the two calibrated templates to learn the binocular stereo calibration information and uses the points from the first set, or the first grid image or points, to select the origin of the real world coordinate system.

connector_pane_image
datatype_icon

binocular stereo session in

Reference to the binocular stereo vision session on which this node operates.

datatype_icon

left calibration template

Calibrated image that represents the single camera information from the left camera in the binocular stereo setup.

datatype_icon

right calibration template

Calibrated image that represents the single camera information from the right camera in the binocular stereo setup.

datatype_icon

rectification options

Information learned to rectify the left and right images.

datatype_icon

learn lookup table?

Boolean that specifies if lookup tables need to be learned to rectify the left and right images.

If this input is set to TRUE, then two lookup tables are computed and are used to rectify the left and right camera images. Using lookup tables drastically improves the rectification speed but comes at a cost of increased memory usage.

datatype_icon

render to original image?

Boolean that specifies learning of a lookup table for mapping disparity image to the original left image.

This option learns one lookup table and can result in increased memory usage and computation overhead.

datatype_icon

scaling factor

Value between 0 and 1 that specifies a value by which the rectified images and disparity images should be scaled.

This parameter is useful for changing the size of the rectified images and the disparity map to speed up the depth reconstruction operation.

datatype_icon

error in

Error conditions that occur before this node runs.

The node responds to this input according to standard error behavior.

Standard Error Behavior

Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.

error in does not contain an error error in contains an error
If no error occurred before the node runs, the node begins execution normally.

If no error occurs while the node runs, it returns no error. If an error does occur while the node runs, it returns that error information as error out.

If an error occurred before the node runs, the node does not execute. Instead, it returns the error in value as error out.

Default: No error

datatype_icon

binocular stereo session out

Reference to the stereo vision session on which this node operates.

datatype_icon

quality

Quality of the stereo calibration that is learned.

datatype_icon

max. projection error

Maximum error in the stereo camera calibration.

The error is computed by projecting the grid points in the left image onto the right image and computing the maximum error obtained between the projected points and the original points in the right image.

datatype_icon

calibration quality

Value between 0 and 1 that indicates the quality of the calibration.

A value of 1 suggests that the calibration is of the best quality. Anything below 0.7 suggests that the system should be calibrated again.

datatype_icon

max. rectification error

Output that indicates how well the rectified images are aligned.

Any value greater than 1.5 indicates that the system should be recalibrated.

datatype_icon

rectification quality

Quality of the rectification process.

A value of 1 specifies that the images are rectified perfectly. A lower value indicates imperfect rectification.

datatype_icon

error out

Error information.

The node produces this output according to standard error behavior.

Standard Error Behavior

Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.

error in does not contain an error error in contains an error
If no error occurred before the node runs, the node begins execution normally.

If no error occurs while the node runs, it returns no error. If an error does occur while the node runs, it returns that error information as error out.

If an error occurred before the node runs, the node does not execute. Instead, it returns the error in value as error out.

Where This Node Can Run:

Desktop OS: Windows

FPGA: Not supported

Web Server: Not supported in VIs that run in a web application


Recently Viewed Topics