Cog3DAlignPattern SubsamplingCubeSizeFineFraction Property Cognex VisionPro
Gets or sets the fraction for determining the fine subsampling cube size to use during training and runtime. This fraction must be greater than zero and less than or equal to one. The product of this fraction and SubsamplingCubeSize specifies the length of one side of the fine subsampling cube.

Namespace: Cognex.VisionPro3D
Assembly: Cognex.VisionPro3D (in Cognex.VisionPro3D.dll) Version: 65.1.0.0
Syntax

public double SubsamplingCubeSizeFineFraction { get; set; }

Property Value

Type: Double
The fraction of the fine subsampling cube size over the coarse subsampling cube size. Default value is 0.75.
Events

Exceptions

ExceptionCondition
ArgumentOutOfRangeException The supplied value is less than or equal to zero, or greater than one.
Remarks

In 3DAlign's multi-resolution search strategy, after the coarse search stage, the tool re-examines found candidate matches at a finer resolution.

The amount of subsampling in the fine resolution is controlled by the fine subsampling cube size, which is a product of SubsamplingCubeSize with SubsamplingCubeSizeFineFraction. This specifies the length of one side of the fine subsampling cube in 3D space.

Note that neither SubsamplingCubeSize nor SubsamplingCubeSizeAutoSelect affects this value, although their combined effects determine the fine subsampling cube size.

The default value of SubsamplingCubeSizeFineFraction works well on a wide variety of patterns and run-time data. Typically you would leave it alone. However, in certain circumstances you might want to adjust it to fit particular needs. For example, when RunMode is RefineStartPose, or when you are working with high-quality input data and need to get higher accuracy in the result pose.

You have direct control over SubsamplingCubeSizeFineFraction. The tool does not attempt to adjust this value even if SubsamplingCubeSizeAutoSelect is "true". Also note that although specifying a very small fraction can result in a nominal fine subsampling cube size smaller than the vision data's voxel size, the tool will internally clamp the effective fine subsampling cube size to the vision data's voxel size.

If you change this value on a trained pattern object, the pattern will become untrained.

See Also