get_deep_matching_3d_paramT_get_deep_matching_3d_paramGetDeepMatching3dParamGetDeepMatching3dParamget_deep_matching_3d_param (Operator)

Name

get_deep_matching_3d_paramT_get_deep_matching_3d_paramGetDeepMatching3dParamGetDeepMatching3dParamget_deep_matching_3d_param — Read a parameter from a Deep 3D Matching model.

Signature

Description

The operator get_deep_matching_3d_paramget_deep_matching_3d_paramGetDeepMatching3dParamGetDeepMatching3dParamget_deep_matching_3d_param returns the parameter values of GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name for the Deep 3D Matching model Deep3DMatchingModelDeep3DMatchingModelDeep3DMatchingModeldeep3DMatchingModeldeep_3dmatching_model in GenParamValueGenParamValueGenParamValuegenParamValuegen_param_value.

The following table gives an overview, which parameters can be set using set_deep_matching_3d_paramset_deep_matching_3d_paramSetDeepMatching3dParamSetDeepMatching3dParamset_deep_matching_3d_param and which can be retrieved using get_deep_matching_3d_paramget_deep_matching_3d_paramGetDeepMatching3dParamGetDeepMatching3dParamget_deep_matching_3d_param.

In the following the parameters are described:

'camera_parameter N'"camera_parameter N""camera_parameter N""camera_parameter N""camera_parameter N", 'camera_pose N'"camera_pose N""camera_pose N""camera_pose N""camera_pose N", 'delete_cameras'"delete_cameras""delete_cameras""delete_cameras""delete_cameras":

These parameters control the camera setup used for matching, i.e., the camera poses and the camera parameters. 'delete_cameras'"delete_cameras""delete_cameras""delete_cameras""delete_cameras" can be set with an empty tuple as value to delete all cameras from a Deep 3D Matching model.

The keys for accessing the parameters of the N'th camera are 'camera_parameter N'"camera_parameter N""camera_parameter N""camera_parameter N""camera_parameter N" and 'camera_pose N'"camera_pose N""camera_pose N""camera_pose N""camera_pose N", where N is the zero-based index of the camera. For example, to access the parameters of the first camera, use 'camera_parameter 0'"camera_parameter 0""camera_parameter 0""camera_parameter 0""camera_parameter 0" and 'camera_pose 0'"camera_pose 0""camera_pose 0""camera_pose 0""camera_pose 0". Note that cameras must be added in order.

Further note that the camera parameters should not contain any distortion. It is recommended to remove any distortion from the camera parameters and images beforehand, using, for example, change_radial_distortion_cam_parchange_radial_distortion_cam_parChangeRadialDistortionCamParChangeRadialDistortionCamParchange_radial_distortion_cam_par in combination with change_radial_distortion_imagechange_radial_distortion_imageChangeRadialDistortionImageChangeRadialDistortionImagechange_radial_distortion_image or gen_radial_distortion_mapgen_radial_distortion_mapGenRadialDistortionMapGenRadialDistortionMapgen_radial_distortion_map and map_imagemap_imageMapImageMapImagemap_image.

The camera pose is the pose of the camera in an arbitrary world coordinate system. The poses of detected objects are returned in that world coordinate system. The angles must be passed in radians.

'dl_model_detection'"dl_model_detection""dl_model_detection""dl_model_detection""dl_model_detection", 'dl_model_pose_estimation'"dl_model_pose_estimation""dl_model_pose_estimation""dl_model_pose_estimation""dl_model_pose_estimation":

The deep learning models used for Deep 3D Matching. Both models are already pre-trained for the target object. They can be obtained and written back in order to, optimize it using optimize_dl_model_for_inferenceoptimize_dl_model_for_inferenceOptimizeDlModelForInferenceOptimizeDlModelForInferenceoptimize_dl_model_for_inference or change the device on which they are executed.

'min_num_views'"min_num_views""min_num_views""min_num_views""min_num_views":

This parameter determines the minimum number of cameras in which an instance must be visible in order to be returned by apply_deep_matching_3dapply_deep_matching_3dApplyDeepMatching3dApplyDeepMatching3dapply_deep_matching_3d. The parameter can be either an integer larger than zero, or the string 'auto'"auto""auto""auto""auto". If 'auto'"auto""auto""auto""auto", instances must be visible in a single camera if only a single camera is used, and in at least two cameras otherwise.

Suggested values: 'auto'"auto""auto""auto""auto", 2, 3

Default: 'auto'"auto""auto""auto""auto"

Value range: .

'min_score'"min_score""min_score""min_score""min_score":

This parameter determines the minimum score of detected instances. In other words, apply_deep_matching_3dapply_deep_matching_3dApplyDeepMatching3dApplyDeepMatching3dapply_deep_matching_3d ignores all detected instances with a score smaller than this value. The score computed by the Deep 3D Matching model lies between 0 and 1, where 0 indicates a bad match and 1 is a very good match.

Value range: [0, .., 1]

Default: 0.2

'num_matches'"num_matches""num_matches""num_matches""num_matches":

This parameter determines the maximum number of matches to return by apply_deep_matching_3dapply_deep_matching_3dApplyDeepMatching3dApplyDeepMatching3dapply_deep_matching_3d. If the operator finds more instances than set in 'num_matches'"num_matches""num_matches""num_matches""num_matches", only the 'num_matches'"num_matches""num_matches""num_matches""num_matches" instances with the highest scores are returned. This parameter can be set to zero, in which case all instances above 'min_score'"min_score""min_score""min_score""min_score" are returned.

Value range: .

Default: 0

'orig_3d_model'"orig_3d_model""orig_3d_model""orig_3d_model""orig_3d_model":

This parameter returns the original 3D CAD model used for creating the Deep 3D Matching model. It can be used to, visualize detection results.

Attention

Deep 3D Matching requires images to not have too much of a distortion. It is recommended to remove any distortion from the camera parameters and images beforehand, using, for example, change_radial_distortion_cam_parchange_radial_distortion_cam_parChangeRadialDistortionCamParChangeRadialDistortionCamParchange_radial_distortion_cam_par in combination with change_radial_distortion_imagechange_radial_distortion_imageChangeRadialDistortionImageChangeRadialDistortionImagechange_radial_distortion_image or gen_radial_distortion_mapgen_radial_distortion_mapGenRadialDistortionMapGenRadialDistortionMapgen_radial_distortion_map and map_imagemap_imageMapImageMapImagemap_image.

Execution Information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).
• Multithreading scope: global (may be called from any thread).
• Automatically parallelized on internal data level.

Parameters

Module

3D Metrology