Table Of Contents

Optical Flow (Optical Flow (LKP)) (G Dataflow)

Last Modified: June 25, 2019

Computes the change in location of a set of feature points between two successive image frames using the pyramid-based Lucas-Kanade algorithm.

connector_pane_image
datatype_icon

current frame

Reference to the current source image.

datatype_icon

previous frame

Reference to the previous source image.

datatype_icon

feature points in

Array of points that need to be tracked.

datatype_icon

x

X-coordinate of the point.

datatype_icon

y

Y-coordinate of the point.

datatype_icon

options

Options that are used to track the features between two successive frames.

datatype_icon

level

Number of pyramid levels to use.

datatype_icon

max. iterations

Number of iterations to run the tracking algorithm at each level.

datatype_icon

window size

Region around each input feature point that is used to search for a match.

datatype_icon

displacement threshold

Minimum allowed displacement between the location of the tracked features from iteration to iteration. That is, if the position of a feature does not move more than the displacement threshold from its location on a previous iteration, the current location of the feature is finalized and it is not tracked anymore.

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

kernel

Coefficients of the filter that is used to smooth the image. The kernel coefficients must be symmetric.

datatype_icon

current frame out

Duplicate of the input current frame.

datatype_icon

distance array

Distance between feature points in and feature points out.

datatype_icon

feature points out

Array of points that represent the new locations of the input feature points in.

datatype_icon

x

X-coordinate of the point.

datatype_icon

y

Y-coordinate of the point.

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