Definition of search parameters. More...
#include <cvb/dnc/search_parameters.hpp>
Public Member Functions | |
SearchParameters ()=default | |
Default search parameters. More... | |
double | HypothesesThreshold () const noexcept |
Get minimum feature score for hypotheses generation. More... | |
void | SetHypothesesThreshold (double value) |
Set minimum feature score for hypotheses generation. More... | |
int | DerivativePatchSize () const noexcept |
Get smoothing area in pixels for gradient and normal calculation. More... | |
void | SetDerivativePatchSize (int value) |
Set smoothing area in pixels for gradient and normal calculation. More... | |
double | IndifferentRadius () const noexcept |
Get fraction of template size which accounts for a single object. More... | |
void | SetIndifferentRadius (double value) |
Set fraction of template size which accounts for a single object. More... | |
int | PartsToFind () const noexcept |
Get the maximum number of objects to find. More... | |
void | SetPartsToFind (int value) |
Set the maximum number of objects to find. More... | |
bool | RawResultsOnly () const noexcept |
Get the raw results flag. More... | |
void | SetRawResultsOnly (bool value) noexcept |
Set the raw results flag. More... | |
int | ICPShrink () const noexcept |
Get the subsample factor for ICP. More... | |
void | SetICPShrink (int value) |
Set the subsample factor for ICP. More... | |
int | ICPMaxIterations () const noexcept |
Get the maximum number of iterations of the ICP algorithm. More... | |
void | SetICPMaxIterations (int value) |
Set the maximum number of iterations of the ICP algorithm. More... | |
double | PrecisionThreshold () const noexcept |
Get precision threshold. More... | |
void | SetPrecisionThreshold (double value) |
Set precision threshold. More... | |
double | MinCoverage () const noexcept |
Get minimum coverage. More... | |
void | SetMinCoverage (double value) |
Set minimum coverage. More... | |
double | MaxOcclusion () const noexcept |
Get maximum occlusion. More... | |
void | SetMaxOcclusion (double value) |
Set maximum occlusion. More... | |
double | MaxInconsistency () const noexcept |
Get maximum inconsistency. More... | |
void | SetMaxInconsistency (double value) |
Set maximum inconsistency. More... | |
double | MinScore () const noexcept |
Get minimum score. More... | |
void | SetMinScore (double value) |
Set minimum score. More... | |
Definition of search parameters.
Search parameters strongly influence the search results. Likewise, they have great influence on the timing of a search operation.
|
default |
Default search parameters.
Does | not throw any exception. |
|
inlinenoexcept |
Get smoothing area in pixels for gradient and normal calculation.
A detailed description of this parameter can be found at the corresponding setting function SetDerivativePatchSize.
Does | not throw any exception. |
|
inlinenoexcept |
Get minimum feature score for hypotheses generation.
A detailed description of this parameter can be found at the corresponding setting function SetHypothesesThreshold.
Does | not throw any exception. |
|
inlinenoexcept |
Get the maximum number of iterations of the ICP algorithm.
A detailed description of this parameter can be found at the corresponding setting function SetICPMaxIterations.
Does | not throw any exception. |
|
inlinenoexcept |
Get the subsample factor for ICP.
A detailed description of this parameter can be found at the corresponding setting function SetICPShrink.
Does | not throw any exception. |
|
inlinenoexcept |
Get fraction of template size which accounts for a single object.
A detailed description of this parameter can be found at the corresponding setting function SetIndifferentRadius.
Does | not throw any exception. |
|
inlinenoexcept |
Get maximum inconsistency.
A detailed description of this parameter can be found at the corresponding setting function SetMaxInconsistency.
Does | not throw any exception. |
|
inlinenoexcept |
Get maximum occlusion.
A detailed description of this parameter can be found at the corresponding setting function SetMaxOcclusion.
Does | not throw any exception. |
|
inlinenoexcept |
Get minimum coverage.
A detailed description of this parameter can be found at the corresponding setting function SetMinCoverage.
Does | not throw any exception. |
|
inlinenoexcept |
Get minimum score.
A detailed description of this parameter can be found at the corresponding setting function SetMinScore.
Does | not throw any exception. |
|
inlinenoexcept |
Get the maximum number of objects to find.
A detailed description of this parameter can be found at the corresponding setting function SetPartsToFind.
Does | not throw any exception. |
|
inlinenoexcept |
Get precision threshold.
A detailed description of this parameter can be found at the corresponding setting function SetPrecisionThreshold.
Does | not throw any exception. |
|
inlinenoexcept |
Get the raw results flag.
A detailed description of this parameter can be found at the corresponding setting function SetRawResultsOnly.
Does | not throw any exception. |
|
inline |
Set smoothing area in pixels for gradient and normal calculation.
This value controls which local environment in the depth image is used to calculate gradients and normals. Minimum is 3. Larger values result in a smoothing of the depth image. This value should be odd. Typical values are in the range 3..9.
[in] | value | The patch size. |
Does | not throw any exception. |
|
inline |
Set minimum feature score for hypotheses generation.
This value controls which areas of the depth image are used as candidates for closer examination. The feature score is calculated from the correspondences of gradients and normals between all models and the actual point cloud data. The threshold should be chosen so that on the one hand all object candidates are found, on the other hand as few false candidates as possible are generated. Typical values are in the range between 0.9 ... 1.0. Disturbances in the point cloud, missing or spurious data may make it necessary to reduce the value. The minimum value is 0.5.
To find a usable threshold it is recommended to set the flag SetRawResultsOnly().
[in] | value | The threshold. |
Does | not throw any exception. |
|
inline |
Set the maximum number of iterations of the ICP algorithm.
This value specifies the maximum number of iterations of the ICP algorithm. Increasing the value may increase the accuracy of the result, while possibly increasing the processing time. A typical value is 10.
[in] | value | The number of iterations. |
Does | not throw any exception. |
|
inline |
Set the subsample factor for ICP.
This value specifies the factor by which the area of a found candidate is reduced before the exact position of the object is determined by means of an ICP algorithm. The minimum allowed value of 1 means no reduction (highest accuracy). With increasing reduction, the processing speed increases, but at the same time the accuracy of the results also decrease. Typical values are in a range 1..4.
[in] | value | The subsample factor. |
Does | not throw any exception. |
|
inline |
Set fraction of template size which accounts for a single object.
This value specifies within which vicinity of a found candidate no further candidates are searched for. The value 1 indicates the largest extent of the learned object. For elongated objects that are close to each other, a smaller value may have to be selected. The minimum value is 0.5.
[in] | value | The indifferent radius. |
Does | not throw any exception. |
|
inline |
Set maximum inconsistency.
This value is a threshold (0..1) that specifies the maximum allowed part of the model view to be insconsistent with the point cloud data in order for the hit to be counted. Inconsistency is defined to be point cloud data which is beyond the model. A typical value may be 0.2. It is influenced by PrecisionThreshold.
[in] | value | The threshold. |
Does | not throw any exception. |
|
inline |
Set maximum occlusion.
This value is a threshold (0..1) that specifies the maximum allowed part of the model view which is occluded by the point cloud data in order for the hit to be counted. Occlusion is defined to be point cloud data lying between the model and the sensor. A typical value may be 0.2. It is influenced by PrecisionThreshold.
[in] | value | The threshold. |
Does | not throw any exception. |
|
inline |
Set minimum coverage.
This value is a threshold (0..1) that specifies the minimum required coverage of the model view by the point cloud data in order for the hit to be counted. A typical value may be 0.8. It is influenced by PrecisionThreshold.
[in] | value | The threshold. |
Does | not throw any exception. |
|
inline |
Set minimum score.
This value is a threshold (0..1) that determines whether the candidate is counted as a hit. For this, a hash similarity score between final model view and point cloud data must exceed this limit. A typical value may be 0.8.
[in] | value | The threshold. |
Does | not throw any exception. |
|
inline |
Set the maximum number of objects to find.
This value specifies the maximum number of objects to be detected. A value of zero means that all objects should be found.
[in] | value | The number of parts to find. |
Does | not throw any exception. |
|
inline |
Set precision threshold.
The calculation of the result score is based on deviations between the CAD model and the point cloud data. This value determines which deviation is considered tolerable, inconsistent or occlusion. This value depends on the quality of the point cloud data. A typical value is 2 mm, the minimum allowed value is 0.
[in] | value | The threshold. |
Does | not throw any exception. |
|
inlinenoexcept |
Set the raw results flag.
If this flag is set, candidate locations are considered as hits without further investigation of these candidates. In this case, only parameters HypothesesThreshold, PartsToFind and MinScore are decisive for finding objects. If found candidates are indeed true object hits, the result values for SearchResult.Position, SearchResult.RotationVector and SearchResult.Theta are only rough in a sense, that no fine tuning (ICP) takes place.
Also, in this case the reported SearchResult.Score values coincide with the feature scores, which makes it possible to determine a useful value for HypothesesThreshold.
[in] | value | True to set on, false otherwise. |
Does | not throw any exception. |