create_planar_uncalib_deformable_model_xldT_create_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld (Operator)

Name

create_planar_uncalib_deformable_model_xldT_create_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld — Prepare a deformable model for planar uncalibrated matching from XLD contours.

Signature

Description

The operator create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld creates a deformable model used for planar uncalibrated matching from the XLD contours passed in ContoursContoursContoursContoursContourscontours. The XLD contours represent the gray-value edges of the object to be searched for. In contrast to the operator create_planar_uncalib_deformable_modelcreate_planar_uncalib_deformable_modelCreatePlanarUncalibDeformableModelcreate_planar_uncalib_deformable_modelCreatePlanarUncalibDeformableModelCreatePlanarUncalibDeformableModel, which creates a deformable model from a template image, the operator create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld creates the deformable model from XLD contours.

The model is generated for multiple image pyramid levels and is stored in memory. The output parameter ModelIDModelIDModelIDModelIDModelIDmodelID is a handle for this model, which is used in subsequent calls to find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel.

The number of pyramid levels is determined with the parameter NumLevelsNumLevelsNumLevelsNumLevelsNumLevelsnumLevels. It should be chosen as large as possible because by this the time necessary to find the object is significantly reduced. On the other hand, NumLevelsNumLevelsNumLevelsNumLevelsNumLevelsnumLevels must be chosen such that the model is still recognizable and contains a sufficient number of points (at least four) on the highest pyramid level. If not enough model points are generated, the number of pyramid levels is reduced internally until enough model points are found on the highest pyramid level. If this procedure leads to a model with no pyramid levels, i.e., if the number of model points is already too small on the lowest pyramid level, create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld returns with an error message. If NumLevelsNumLevelsNumLevelsNumLevelsNumLevelsnumLevels is set to 'auto'"auto""auto""auto""auto""auto", create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld determines the number of pyramid levels automatically. The computed number of pyramid levels can be queried using get_deformable_model_paramsget_deformable_model_paramsGetDeformableModelParamsget_deformable_model_paramsGetDeformableModelParamsGetDeformableModelParams. In rare cases, it might happen that create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld determines a value for the number of pyramid levels that is too large or too small. If the number of pyramid levels is chosen too large, the model may not be recognized in the search image or it may be necessary to select very low parameters for MinScore or Greediness in find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel to find the object. If the number of pyramid levels is chosen too small, the time required to find the object with find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel may increase. In both cases, the number of pyramid levels should be selected manually.

The parameters AngleStartAngleStartAngleStartAngleStartAngleStartangleStart and AngleExtentAngleExtentAngleExtentAngleExtentAngleExtentangleExtent determine the range of possible rotations, in which the object can occur in the image. The parameter AngleStepAngleStepAngleStepAngleStepAngleStepangleStep determines the step length within the selected range of angles. AngleStepAngleStepAngleStepAngleStepAngleStepangleStep should be chosen based on the size of the object. Smaller models do not have many different discrete rotations in the image, and hence AngleStepAngleStepAngleStepAngleStepAngleStepangleStep should be chosen larger for smaller models. If AngleExtentAngleExtentAngleExtentAngleExtentAngleExtentangleExtent is not an integer multiple of AngleStepAngleStepAngleStepAngleStepAngleStepangleStep, AngleStepAngleStepAngleStepAngleStepAngleStepangleStep is modified accordingly. To ensure a sampling of the range of possible rotations that is independent of the given AngleStartAngleStartAngleStartAngleStartAngleStartangleStart, the range of possible rotations is modified as follows: If there is no positive integer value n such that AngleStartAngleStartAngleStartAngleStartAngleStartangleStart plus n times AngleStepAngleStepAngleStepAngleStepAngleStepangleStep is exactly 0.0, AngleStartAngleStartAngleStartAngleStartAngleStartangleStart is decreased by up to AngleStepAngleStepAngleStepAngleStepAngleStepangleStep and AngleExtentAngleExtentAngleExtentAngleExtentAngleExtentangleExtent is increased by AngleStepAngleStepAngleStepAngleStepAngleStepangleStep.

The parameters ScaleRMinScaleRMinScaleRMinScaleRMinScaleRMinscaleRMin, ScaleRMaxScaleRMaxScaleRMaxScaleRMaxScaleRMaxscaleRMax, ScaleCMinScaleCMinScaleCMinScaleCMinScaleCMinscaleCMin, and ScaleCMaxScaleCMaxScaleCMaxScaleCMaxScaleCMaxscaleCMax determine the basic range of anisotropic scales of the object in the row and column direction. A scale of 1 in both scale factors corresponds to the original size of the model. The parameters ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep and ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep determine the step length within the selected range of scales. Like AngleStepAngleStepAngleStepAngleStepAngleStepangleStep, ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep and ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep should be chosen based on the size of the object. If the respective range of scales is not an integer multiple of ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep and ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep, ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep and ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep are modified accordingly. To ensure a sampling of the range of possible scales that is independent of the given ScaleRMinScaleRMinScaleRMinScaleRMinScaleRMinscaleRMin and ScaleCMinScaleCMinScaleCMinScaleCMinScaleCMinscaleCMin, the range of possible scales is modified as follows: If there are no positive integer values n and m such that ScaleRMinScaleRMinScaleRMinScaleRMinScaleRMinscaleRMin plus n times ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep is exactly 0.0 and ScaleCMinScaleCMinScaleCMinScaleCMinScaleCMinscaleCMin plus m times ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep is exactly 0.0, ScaleRMinScaleRMinScaleRMinScaleRMinScaleRMinscaleRMin and ScaleCMinScaleCMinScaleCMinScaleCMinScaleCMinscaleCMin are decreased by up to ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep and ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep, respectively, and ScaleRMaxScaleRMaxScaleRMaxScaleRMaxScaleRMaxscaleRMax and ScaleCMaxScaleCMaxScaleCMaxScaleCMaxScaleCMaxscaleCMax are increased such that the range of possible scales is increased by ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep and ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep, respectively.

Note that the transformations are treated internally such that the scalings are applied first, followed by the rotation. Therefore, the model should usually be aligned such that it appears horizontally or vertically.

If AngleStepAngleStepAngleStepAngleStepAngleStepangleStep = 'auto'"auto""auto""auto""auto""auto" or ScaleRStepScaleRStepScaleRStepScaleRStepScaleRStepscaleRStep, ScaleCStepScaleCStepScaleCStepScaleCStepScaleCStepscaleCStep = 'auto'"auto""auto""auto""auto""auto" is selected, create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld automatically determines a suitable angle or scale step length, respectively, based on the size of the model. The automatically computed angle and scale step lengths can be queried using get_deformable_model_paramsget_deformable_model_paramsGetDeformableModelParamsget_deformable_model_paramsGetDeformableModelParamsGetDeformableModelParams.

For particularly large models, it may be useful to reduce the number of model points by setting OptimizationOptimizationOptimizationOptimizationOptimizationoptimization to a value different from 'none'"none""none""none""none""none". If OptimizationOptimizationOptimizationOptimizationOptimizationoptimization = 'none'"none""none""none""none""none" is set, all model points are stored. In all other cases, the number of points is reduced according to the value of OptimizationOptimizationOptimizationOptimizationOptimizationoptimization. If the number of points is reduced, it may be necessary in find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel to set the parameter Greediness to a smaller value, e.g., 0.7 or 0.8. For small models, the reduction of the number of model points does not result in a speed-up of the search, because in this case usually significantly more potential instances of the model must be examined. If OptimizationOptimizationOptimizationOptimizationOptimizationoptimization is set to 'auto'"auto""auto""auto""auto""auto", create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld automatically determines the reduction of the number of model points.

With MinContrastMinContrastMinContrastMinContrastMinContrastminContrast, it can be determined which contrast the object contours must at least have in the recognition performed by find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel. In other words, this parameter separates the object from the noise in the image. Therefore, a good choice is the range of gray-value changes caused by the noise in the image. If, e.g., the gray values fluctuate within a range of 10 gray levels, MinContrastMinContrastMinContrastMinContrastMinContrastminContrast should be set to 10. If multi-channel images are used for the model and the search images, and if the parameter MetricMetricMetricMetricMetricmetric is set to 'ignore_color_polarity'"ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity" (see below) the noise in one channel must be multiplied by the square root of the number of channels to determine MinContrastMinContrastMinContrastMinContrastMinContrastminContrast. If, e.g., the gray values fluctuate within a range of 10 gray levels in a single channel and the image is a three-channel image, MinContrastMinContrastMinContrastMinContrastMinContrastminContrast should be set to 17. If the model should be recognized in very low contrast images, MinContrastMinContrastMinContrastMinContrastMinContrastminContrast must be set to a correspondingly small value. If the model should be recognized even if it is severely occluded, MinContrastMinContrastMinContrastMinContrastMinContrastminContrast should be slightly larger than the range of gray value fluctuations created by noise to ensure that the position and rotation of the model are extracted robustly and accurately by find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel.

The parameter MetricMetricMetricMetricMetricmetric determines the conditions under which the model is recognized in the image. If MetricMetricMetricMetricMetricmetric = 'use_polarity'"use_polarity""use_polarity""use_polarity""use_polarity""use_polarity", the object in the image and the model must have the same contrast. If, e.g., the model is a bright object on a dark background, the object is found only if it is also brighter than the background. If MetricMetricMetricMetricMetricmetric = 'ignore_global_polarity'"ignore_global_polarity""ignore_global_polarity""ignore_global_polarity""ignore_global_polarity""ignore_global_polarity", the object is found in the image also if the contrast reverses globally. In the above example, the object hence is also found if it is darker than the background. The runtime of find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel will increase slightly in this case. If MetricMetricMetricMetricMetricmetric = 'ignore_part_polarity'"ignore_part_polarity""ignore_part_polarity""ignore_part_polarity""ignore_part_polarity""ignore_part_polarity" or MetricMetricMetricMetricMetricmetric = 'ignore_local_polarity'"ignore_local_polarity""ignore_local_polarity""ignore_local_polarity""ignore_local_polarity""ignore_local_polarity", the model is found even if the contrast changes locally. These modes can, e.g., be useful if the object consists of a part with a medium gray value, within which either darker or brighter sub-objects lie. The above mentioned four metrics can only be applied to single-channel images. If a multi-channel image is used as the search image, only the first channel will be used (and no error message will be returned). If MetricMetricMetricMetricMetricmetric = 'ignore_color_polarity'"ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity", the model is found even if the color contrast changes locally. This is, e.g., the case if parts of the object can change their color, e.g., from red to green. In particular, this mode is useful if it is not known in advance in which channels the object is visible. In this mode, the runtime of find_planar_calib_deformable_modelfind_planar_calib_deformable_modelFindPlanarCalibDeformableModelfind_planar_calib_deformable_modelFindPlanarCalibDeformableModelFindPlanarCalibDeformableModel can also increase significantly. The metric 'ignore_color_polarity'"ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity" can be used for images with an arbitrary number of channels. If it is used for single-channel images, it has the same effect as 'ignore_local_polarity'"ignore_local_polarity""ignore_local_polarity""ignore_local_polarity""ignore_local_polarity""ignore_local_polarity". It should be noted that for MetricMetricMetricMetricMetricmetric = 'ignore_color_polarity'"ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity""ignore_color_polarity" the channels do not need to contain a spectral subdivision of the light (like in an RGB image). The channels can, e.g., also contain images of the same object that were obtained by illuminating the object from different directions. Note that the first two metrics ('use_polarity'"use_polarity""use_polarity""use_polarity""use_polarity""use_polarity" and 'ignore_global_polarity'"ignore_global_polarity""ignore_global_polarity""ignore_global_polarity""ignore_global_polarity""ignore_global_polarity") can only be selected if all ContoursContoursContoursContoursContourscontours provide the attribute 'edge_direction'"edge_direction""edge_direction""edge_direction""edge_direction""edge_direction", which defines the polarity of the contained contours. This attribute is available for contours created, e.g., with edges_sub_pixedges_sub_pixEdgesSubPixedges_sub_pixEdgesSubPixEdgesSubPix with the parameter MethodMethodMethodMethodMethodmethod set to, e.g., 'canny'"canny""canny""canny""canny""canny". Otherwise, these two metrics can be selected with the operator set_planar_uncalib_deformable_model_metricset_planar_uncalib_deformable_model_metricSetPlanarUncalibDeformableModelMetricset_planar_uncalib_deformable_model_metricSetPlanarUncalibDeformableModelMetricSetPlanarUncalibDeformableModelMetric, which determines the polarity of the model contours from a representative image.

The center of gravity of the smallest surrounding rectangle of the ContoursContoursContoursContoursContourscontours is used as the origin (reference point) of the model. A different origin can be set with set_deformable_model_originset_deformable_model_originSetDeformableModelOriginset_deformable_model_originSetDeformableModelOriginSetDeformableModelOrigin.

Attention

Note that, in contrast to the operator create_planar_uncalib_deformable_modelcreate_planar_uncalib_deformable_modelCreatePlanarUncalibDeformableModelcreate_planar_uncalib_deformable_modelCreatePlanarUncalibDeformableModelCreatePlanarUncalibDeformableModel, it is not possible to specify a minimum size of the model components. To avoid small model components in the model, short contours can be eliminated before calling create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld with the operator select_contours_xldselect_contours_xldSelectContoursXldselect_contours_xldSelectContoursXldSelectContoursXld.

Parallelization

• Multithreading type: exclusive (runs in parallel only with independent operators).
• Multithreading scope: global (may be called from any thread).
• Processed without parallelization.

Parameters

Result

If the parameters are valid, the operator create_planar_uncalib_deformable_model_xldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldcreate_planar_uncalib_deformable_model_xldCreatePlanarUncalibDeformableModelXldCreatePlanarUncalibDeformableModelXld returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised. If the parameter NumLevelsNumLevelsNumLevelsNumLevelsNumLevelsnumLevels is chosen such that the model contains too few points, the error 8510 is raised.

Possible Predecessors

read_contour_xld_dxfread_contour_xld_dxfReadContourXldDxfread_contour_xld_dxfReadContourXldDxfReadContourXldDxf, edges_sub_pixedges_sub_pixEdgesSubPixedges_sub_pixEdgesSubPixEdgesSubPix, select_contours_xldselect_contours_xldSelectContoursXldselect_contours_xldSelectContoursXldSelectContoursXld

Possible Successors

find_planar_uncalib_deformable_modelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelfind_planar_uncalib_deformable_modelFindPlanarUncalibDeformableModelFindPlanarUncalibDeformableModel

See also

create_planar_uncalib_deformable_modelcreate_planar_uncalib_deformable_modelCreatePlanarUncalibDeformableModelcreate_planar_uncalib_deformable_modelCreatePlanarUncalibDeformableModelCreatePlanarUncalibDeformableModel

Module

Matching