CVBpy 14.0
TeachParameters Class Reference

Parameters for teaching a DNC finder. More...

Inherits object.

Properties

 derivative_patch_size = property
 int: Get or set smoothing area in pixels for gradient and normal calculation. More...
 
 distance_kernel_size = property
 float: Get or set the factor for Distance transform calculation. More...
 
 height_sensitivity = property
 float: Get or set the minimum gradient magnitude to accept a local gradient as a feature in the depth images. More...
 
 icp_shrink = property
 int: Get or set the subsample factor for ICP. More...
 
 local_distribution_size = property
 int: Get or set the size of area in which local features are distributed (in pixels). More...
 
 num_gradient_features = property
 int: Get or set the number of gradient features retained in the classifier. More...
 
 num_normal_features = property
 int: Get or set the number of normal vector features retained in the classifier. More...
 

Detailed Description

Parameters for teaching a DNC finder.

Default teach parameters.

Property Documentation

◆ derivative_patch_size

derivative_patch_size = property
static

int: Get or set smoothing area in pixels for gradient and normal calculation.

The value controls the local environment in the depth images of the examples which is used to calculate gradients and normals.Minimum is 3. Larger values effectively result in a smoothing of the depth images. The value should be odd. Typical values are in the range 3..9.Smaller values should be favored, since the example images of the CAD object are flawless and free of noise.The corresponding value of cvb.dnc.SearchParameters.derivative_patch_size of a detection task should be equal, or - in case of sensor noise - bigger. The minimum value is 3.

◆ distance_kernel_size

distance_kernel_size = property
static

float: Get or set the factor for Distance transform calculation.

A so called Huber kernel is used for the calculation of a distance transform of an example. To some extend a Huber kernel can possibly enlarge the convergence basin of ICP - operations, relative to the Euclidian distance transform(factor = 1). A recommended value is 2. The minimum value is 1.

◆ height_sensitivity

height_sensitivity = property
static

float: Get or set the minimum gradient magnitude to accept a local gradient as a feature in the depth images.

The value specifies a threshold (in millimeters) above which local height changes are observed as characteristic features. A typical value is 1 mm. This value is also used implicitly during later search tasks. The minimum value is 0.0.

◆ icp_shrink

icp_shrink = property
static

int: Get or set the subsample factor for ICP.

To speed up search tasks, a voxel representation of the examples is pre-calculated. The subsample factor determins the amount of data used to perform an ICP - operation.It strongly influences the recognition speed and the amount of memory used.The recommended value is 4. The minimum value is 1.

◆ local_distribution_size

local_distribution_size = property
static

int: Get or set the size of area in which local features are distributed (in pixels).

To account for the finite and discrete example positions the local features are somewhat smeared out. This value specifies the local active range of a single feature. A typical value is 8. The minimum value is 0.

◆ num_gradient_features

num_gradient_features = property
static

int: Get or set the number of gradient features retained in the classifier.

To speed up the calculation of correspondences during a detection task, the possibly dense gradient features from the examples are thinned out to a minimum necessary number. This number strongly depends on the object itself.Typical values are between 100 and 1000. A value of 0 means that all gradient features should be used. The minimum value is 0.

◆ num_normal_features

num_normal_features = property
static

int: Get or set the number of normal vector features retained in the classifier.

To speed up the calculation of correspondences during a detection task, the dense normal features from the examples are thinned out to a minimum necessary number. This number strongly depends on the object itself.Typical values are between 100 and 1000. A value of 0 means that all normal features should be used. The minimum value is 0.