open3d.pipelines.odometry.RGBDOdometryJacobianFromColorTerm#

class open3d.pipelines.odometry.RGBDOdometryJacobianFromColorTerm#

Class to Compute Jacobian using color term.

Energy: \((I_p-I_q)^2.\)

Reference:

  1. Steinbrucker, J. Sturm, and D. Cremers.

Real-time visual odometry from dense RGB-D images.

In ICCV Workshops, 2011.

__init__(*args, **kwargs)#

Overloaded function.

  1. __init__(self: open3d.cpu.pybind.pipelines.odometry.RGBDOdometryJacobianFromColorTerm) -> None

Default constructor

  1. __init__(self: open3d.cpu.pybind.pipelines.odometry.RGBDOdometryJacobianFromColorTerm, arg0: open3d.cpu.pybind.pipelines.odometry.RGBDOdometryJacobianFromColorTerm) -> None

Copy constructor

compute_jacobian_and_residual(self: open3d.cpu.pybind.pipelines.odometry.RGBDOdometryJacobian, Function to compute i-th row of J and r the vector form of J_r is basically 6x1 matrix, but it can be easily extendable to 6xn matrix. See RGBDOdometryJacobianFromHybridTerm for this case.row: int, J_r: List[numpy.ndarray[numpy.float64[6, 1]]], r: open3d.cpu.pybind.utility.DoubleVector, w: open3d.cpu.pybind.utility.DoubleVector, source: open3d.cpu.pybind.geometry.RGBDImage, target: open3d.cpu.pybind.geometry.RGBDImage, source_xyz: open3d.cpu.pybind.geometry.Image, target_dx: open3d.cpu.pybind.geometry.RGBDImage, target_dy: open3d.cpu.pybind.geometry.RGBDImage, intrinsic: numpy.ndarray[numpy.float64[3, 3]], extrinsic: numpy.ndarray[numpy.float64[4, 4]], corresps: open3d.cpu.pybind.utility.Vector4iVector) → None#