open3d.t.pipelines.registration.TransformationEstimationForDopplerICP#

class open3d.t.pipelines.registration.TransformationEstimationForDopplerICP#

Class to estimate a transformation between two point clouds using color information

__init__(*args, **kwargs)#

Overloaded function.

  1. __init__(self: open3d.cpu.pybind.t.pipelines.registration.TransformationEstimationForDopplerICP) -> None

Default constructor

  1. __init__(self: open3d.cpu.pybind.t.pipelines.registration.TransformationEstimationForDopplerICP, arg0: open3d.cpu.pybind.t.pipelines.registration.TransformationEstimationForDopplerICP) -> None

Copy constructor

  1. __init__(self: open3d.cpu.pybind.t.pipelines.registration.TransformationEstimationForDopplerICP, period: float, lambda_doppler: float, reject_dynamic_outliers: bool, doppler_outlier_threshold: float, outlier_rejection_min_iteration: int, geometric_robust_loss_min_iteration: int, doppler_robust_loss_min_iteration: int, goemetric_kernel: open3d.cpu.pybind.t.pipelines.registration.robust_kernel.RobustKernel, doppler_kernel: open3d.cpu.pybind.t.pipelines.registration.robust_kernel.RobustKernel, transform_vehicle_to_sensor: open3d.cpu.pybind.core.Tensor) -> None

  2. __init__(self: open3d.cpu.pybind.t.pipelines.registration.TransformationEstimationForDopplerICP, lambda_doppler: float) -> None

compute_rmse(self, source, target, correspondences)#

Compute RMSE between source and target points cloud given correspondences.

Parameters:

  • source (open3d.t.geometry.PointCloud) – Source point cloud.

  • target (open3d.t.geometry.PointCloud) – Target point cloud.

  • correspondences (open3d.core.Tensor) – Tensor of type Int64 containing indices of corresponding target points, where the value is the target index and the index of the value itself is the source index. It contains -1 as value at index with no correspondence.

Returns:

float

compute_transformation(self: open3d.cpu.pybind.t.pipelines.registration.TransformationEstimationForDopplerICP, arg0: open3d.cpu.pybind.t.geometry.PointCloud, arg1: open3d.cpu.pybind.t.geometry.PointCloud, arg2: open3d.cpu.pybind.core.Tensor, arg3: open3d.cpu.pybind.core.Tensor, arg4: int) → open3d.cpu.pybind.core.Tensor#

Compute transformation from source to target point cloud given correspondences

property doppler_kernel#

Robust Kernel used in the Doppler Error Optimization

property doppler_outlier_threshold#

Correspondences with Doppler error greater than this threshold are rejected from optimization.

property doppler_robust_loss_min_iteration#

Minimum iterations after which Robust Kernel is used for the Doppler error

property geometric_kernel#

Robust Kernel used in the Geometric Error Optimization

property geometric_robust_loss_min_iteration#

Minimum iterations after which Robust Kernel is used for the Geometric error

property lambda_doppler#

λ ∈ [0, 1] in the overall energy (1−λ)EG + λED. Refer the documentation of DopplerICP for more information.

property outlier_rejection_min_iteration#

Number of iterations of ICP after which outlier rejection is enabled.

property period#

Time period (in seconds) between the source and the target point clouds.

property reject_dynamic_outliers#

Whether or not to reject dynamic point outlier correspondences.

property transform_vehicle_to_sensor#

The 4x4 extrinsic transformation matrix between the vehicle and the sensor frames.