find_deformable_surface_modelT_find_deformable_surface_modelFindDeformableSurfaceModelFindDeformableSurfaceModelfind_deformable_surface_model (算子)

名称

find_deformable_surface_modelT_find_deformable_surface_modelFindDeformableSurfaceModelFindDeformableSurfaceModelfind_deformable_surface_model — 在三维场景中找到可变形表面模型的最佳匹配。

签名

描述

算子 find_deformable_surface_modelfind_deformable_surface_modelFindDeformableSurfaceModelFindDeformableSurfaceModelFindDeformableSurfaceModelfind_deformable_surface_model finds the best match of the deformable surface model DeformableSurfaceModelDeformableSurfaceModelDeformableSurfaceModelDeformableSurfaceModeldeformableSurfaceModeldeformable_surface_model in the 3D scene ObjectModel3DObjectModel3DObjectModel3DObjectModel3DobjectModel3Dobject_model_3d. The deformable surface model must have been created previously with, for example, create_deformable_surface_modelcreate_deformable_surface_modelCreateDeformableSurfaceModelCreateDeformableSurfaceModelCreateDeformableSurfaceModelcreate_deformable_surface_model。

The matching requires that the 3D object model ObjectModel3DObjectModel3DObjectModel3DObjectModel3DobjectModel3Dobject_model_3d contains points and normals. The scene shall provide one of the following options:

• points and point normals

• points and a 2D-Mapping, e.g., an XYZ image triple converted with xyz_to_object_model_3dxyz_to_object_model_3dXyzToObjectModel3dXyzToObjectModel3dXyzToObjectModel3dxyz_to_object_model_3d

It is important for an accurate pose that the normals of the scene and the model point in the same direction (see 'scene_invert_normals'"scene_invert_normals""scene_invert_normals""scene_invert_normals""scene_invert_normals""scene_invert_normals"). Note that triangles or polygons in the passed scene are ignored. Instead, only the vertices are used for matching. It is thus in general not recommended to use this operator on meshed scenes, such as CAD data. Instead, such a scene must be sampled beforehand using sample_object_model_3dsample_object_model_3dSampleObjectModel3dSampleObjectModel3dSampleObjectModel3dsample_object_model_3d to create points and normals. When using noisy point clouds, e.g., from time-of-flight cameras, the generic parameter 'scene_normal_computation'"scene_normal_computation""scene_normal_computation""scene_normal_computation""scene_normal_computation""scene_normal_computation" should be set to 'mls'"mls""mls""mls""mls""mls" in order to obtain more robust results (see below).

First, points are sampled uniformly from the scene passed in ObjectModel3DObjectModel3DObjectModel3DObjectModel3DobjectModel3Dobject_model_3d. The sampling distance is controlled with the parameter RelSamplingDistanceRelSamplingDistanceRelSamplingDistanceRelSamplingDistancerelSamplingDistancerel_sampling_distance, and is given relative to the diameter of the surface model. Decreasing RelSamplingDistanceRelSamplingDistanceRelSamplingDistanceRelSamplingDistancerelSamplingDistancerel_sampling_distance leads to more sampled points, and in turn to a more stable but slower matching. Increasing RelSamplingDistanceRelSamplingDistanceRelSamplingDistanceRelSamplingDistancerelSamplingDistancerel_sampling_distance reduces the number of sampled scene points, which leads to a less stable but faster matching. For an illustration showing different values for RelSamplingDistanceRelSamplingDistanceRelSamplingDistanceRelSamplingDistancerelSamplingDistancerel_sampling_distance, please refer to the operator create_deformable_surface_modelcreate_deformable_surface_modelCreateDeformableSurfaceModelCreateDeformableSurfaceModelCreateDeformableSurfaceModelcreate_deformable_surface_model。

The operator get_deformable_surface_matching_resultget_deformable_surface_matching_resultGetDeformableSurfaceMatchingResultGetDeformableSurfaceMatchingResultGetDeformableSurfaceMatchingResultget_deformable_surface_matching_result can be used to retrieve the sampled scene points for visual inspection. For a robust matching it is recommended that at least 50-100 scene points are sampled for each object instance.

The method first finds an approximate position of the object. This position is then refined. The generic parameters controlling the deformation are described further down.

If a match was found, the score of the match is returned in ScoreScoreScoreScorescorescore and a deformable surface matching result handle is returned in DeformableSurfaceMatchingResultDeformableSurfaceMatchingResultDeformableSurfaceMatchingResultDeformableSurfaceMatchingResultdeformableSurfaceMatchingResultdeformable_surface_matching_result. Details of the matching result, such as the deformed model and the position of the reference points, can be queried with the operator get_deformable_surface_matching_resultget_deformable_surface_matching_resultGetDeformableSurfaceMatchingResultGetDeformableSurfaceMatchingResultGetDeformableSurfaceMatchingResultget_deformable_surface_matching_result using the result handle.

The score is normalized between 0 and 1 and represents the amount of model surface visible in the scene. A value of 1 represents a perfect match. The parameter MinScoreMinScoreMinScoreMinScoreminScoremin_score can be used to filter the result. A match is returned only if its score exceeds the value of MinScoreMinScoreMinScoreMinScoreminScoremin_score。

The parameters GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name and GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value are used to set generic parameters. Both get a tuple of equal length, where the tuple passed to GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name contains the names of the parameters to set, and the tuple passed to GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value contains the corresponding values. The possible parameter names and values are described below.

'scene_normal_computation'"scene_normal_computation""scene_normal_computation""scene_normal_computation""scene_normal_computation""scene_normal_computation"：

This parameter controls the normal computation of the sampled scene. In the default mode 'fast'"fast""fast""fast""fast""fast", normals are computed based on a small neighborhood of points. In the mode 'mls'"mls""mls""mls""mls""mls", normals are computed based on a larger neighborhood and using the more complex but more accurate 'mls'"mls""mls""mls""mls""mls" method. A more detailed description of the 'mls'"mls""mls""mls""mls""mls" method can be found in the description of the operator surface_normals_object_model_3dsurface_normals_object_model_3dSurfaceNormalsObjectModel3dSurfaceNormalsObjectModel3dSurfaceNormalsObjectModel3dsurface_normals_object_model_3d。The 'mls'"mls""mls""mls""mls""mls" mode is intended for noisy data, such as images from time-of-flight cameras.

值列表： 'fast'"fast""fast""fast""fast""fast", 'mls'"mls""mls""mls""mls""mls"

默认值： 'fast'"fast""fast""fast""fast""fast"

'scene_invert_normals'"scene_invert_normals""scene_invert_normals""scene_invert_normals""scene_invert_normals""scene_invert_normals"：

Invert the orientation of the surface normals of the scene. The orientation of surface normals of the scene have to match with the orientation of the model. If both the model and the scene are acquired with the same setup, the normals will already point in the same direction. If you experience the effect that the model is found on the 'outside' of the scene surface, try to set this parameter to 'true'"true""true""true""true""true". Also, make sure that the normals in the scene all point either outward or inward, i.e., are oriented consistently.

Possible values: 'false'"false""false""false""false""false", 'true'"true""true""true""true""true"

默认值： 'false'"false""false""false""false""false"

'pose_ref_num_steps'"pose_ref_num_steps""pose_ref_num_steps""pose_ref_num_steps""pose_ref_num_steps""pose_ref_num_steps"：

Number of iterations for the refinement. Increasing the number of iteration leads to a more accurate position at the expense of runtime. However, once convergence is reached, the accuracy can no longer be increased, even if the number of steps is increased.

建议值： 1, 10, 25, 50

默认值： 25

Assertion: 'pose_ref_num_steps'"pose_ref_num_steps""pose_ref_num_steps""pose_ref_num_steps""pose_ref_num_steps""pose_ref_num_steps" > 0

'pose_ref_dist_threshold_rel'"pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel"：

Set the distance threshold for refinement relative to the diameter of the surface model. Only scene points that are closer to the object than this distance are used for the optimization. Scene points further away are ignored.

建议值： 0.05, 0.1, 0.25, 0.3

默认值： 0.25

Assertion: 0 < 'pose_ref_dist_threshold_rel'"pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel"

'pose_ref_dist_threshold_abs'"pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs"：

Set the distance threshold for dense pose refinement as absolute value. See 'pose_ref_dist_threshold_rel'"pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel" for a detailed description. Only one of the parameters 'pose_ref_dist_threshold_rel'"pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel""pose_ref_dist_threshold_rel" and 'pose_ref_dist_threshold_abs'"pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs" can be set. If both are set, only the value of the last parameter is used.

Assertion: 0 < 'pose_ref_dist_threshold_abs'"pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs""pose_ref_dist_threshold_abs"

'pose_ref_scoring_dist_rel'"pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel"：

Set the distance threshold for scoring relative to the diameter of the surface model. See the following 'pose_ref_scoring_dist_abs'"pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs" for a detailed description. Only one of the parameters 'pose_ref_scoring_dist_rel'"pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel" and 'pose_ref_scoring_dist_abs'"pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs" can be set. If both are set, only the value of the last parameter is used.

建议值： 0.1, 0.05, 0.03, 0.005

默认值： 0.03

Assertion: 0 < 'pose_ref_scoring_dist_rel'"pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel"

'pose_ref_scoring_dist_abs'"pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs"：

Set the distance threshold for scoring. Only scene points that are closer to the object than this distance are considered to be 'on the model' when computing the score after the refinement. All other scene points are considered not to be on the model. The value should correspond to the amount of noise on the coordinates of the scene points. Only one of the parameters 'pose_ref_scoring_dist_rel'"pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel""pose_ref_scoring_dist_rel" and 'pose_ref_scoring_dist_abs'"pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs" can be set. If both are set, only the value of the last parameter is used.

Assertion: 0 < 'pose_ref_scoring_dist_abs'"pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs""pose_ref_scoring_dist_abs"

执行信息

• 多线程类型：可重入（与非独占算子并行运行）。
• 多线程作用域：全局（可从任何线程调用）。
• 在内部数据级别上自动并行化。

此算子返回一个句柄。请注意，即使该句柄被用作特定算子的输入参数，这些算子仍可能改变此句柄类型的实例状态。

此算子支持取消超时和中断。

参数

结果

find_deformable_surface_modelfind_deformable_surface_modelFindDeformableSurfaceModelFindDeformableSurfaceModelFindDeformableSurfaceModelfind_deformable_surface_model 在所有参数正确时返回 2 ( H_MSG_TRUE )。如有必要，则抛出异常。

可能的前趋

read_object_model_3dread_object_model_3dReadObjectModel3dReadObjectModel3dReadObjectModel3dread_object_model_3d, xyz_to_object_model_3dxyz_to_object_model_3dXyzToObjectModel3dXyzToObjectModel3dXyzToObjectModel3dxyz_to_object_model_3d, get_object_model_3d_paramsget_object_model_3d_paramsGetObjectModel3dParamsGetObjectModel3dParamsGetObjectModel3dParamsget_object_model_3d_params, read_deformable_surface_modelread_deformable_surface_modelReadDeformableSurfaceModelReadDeformableSurfaceModelReadDeformableSurfaceModelread_deformable_surface_model, create_deformable_surface_modelcreate_deformable_surface_modelCreateDeformableSurfaceModelCreateDeformableSurfaceModelCreateDeformableSurfaceModelcreate_deformable_surface_model, get_deformable_surface_model_paramget_deformable_surface_model_paramGetDeformableSurfaceModelParamGetDeformableSurfaceModelParamGetDeformableSurfaceModelParamget_deformable_surface_model_param, add_deformable_surface_model_reference_pointadd_deformable_surface_model_reference_pointAddDeformableSurfaceModelReferencePointAddDeformableSurfaceModelReferencePointAddDeformableSurfaceModelReferencePointadd_deformable_surface_model_reference_point, add_deformable_surface_model_sampleadd_deformable_surface_model_sampleAddDeformableSurfaceModelSampleAddDeformableSurfaceModelSampleAddDeformableSurfaceModelSampleadd_deformable_surface_model_sample

可能的后继

refine_deformable_surface_modelrefine_deformable_surface_modelRefineDeformableSurfaceModelRefineDeformableSurfaceModelRefineDeformableSurfaceModelrefine_deformable_surface_model, get_deformable_surface_matching_resultget_deformable_surface_matching_resultGetDeformableSurfaceMatchingResultGetDeformableSurfaceMatchingResultGetDeformableSurfaceMatchingResultget_deformable_surface_matching_result, clear_deformable_surface_matching_resultclear_deformable_surface_matching_resultClearDeformableSurfaceMatchingResultClearDeformableSurfaceMatchingResultClearDeformableSurfaceMatchingResultclear_deformable_surface_matching_result, clear_object_model_3dclear_object_model_3dClearObjectModel3dClearObjectModel3dClearObjectModel3dclear_object_model_3d

替代

refine_deformable_surface_modelrefine_deformable_surface_modelRefineDeformableSurfaceModelRefineDeformableSurfaceModelRefineDeformableSurfaceModelrefine_deformable_surface_model

另见

refine_deformable_surface_modelrefine_deformable_surface_modelRefineDeformableSurfaceModelRefineDeformableSurfaceModelRefineDeformableSurfaceModelrefine_deformable_surface_model

模块

三维计量

---