View Source Evision.PPFMatch3D.ICP (Evision v0.2.9)
Summary
Types
@type t() :: %Evision.PPFMatch3D.ICP{ref: reference()}
Type that represents an PPFMatch3D.ICP
struct.
ref.
reference()
The underlying erlang resource variable.
Functions
ICP
Return
- self:
ICP
Python prototype (for reference only):
ICP() -> <ppf_match_3d_ICP object>
@spec iCP(Keyword.t()) :: any() | {:error, String.t()}
@spec iCP(integer()) :: t() | {:error, String.t()}
ICP
Positional Arguments
- iterations:
integer()
Keyword Arguments
- tolerence:
float
. - rejectionScale:
float
. - numLevels:
integer()
. - sampleType:
integer()
. - numMaxCorr:
integer()
.
Return
self:
ICP
\brief ICP constructor with default arguments.
Python prototype (for reference only):
ICP(iterations[, tolerence[, rejectionScale[, numLevels[, sampleType[, numMaxCorr]]]]]) -> <ppf_match_3d_ICP object>
@spec iCP( integer(), [ numLevels: term(), numMaxCorr: term(), rejectionScale: term(), sampleType: term(), tolerence: term() ] | nil ) :: t() | {:error, String.t()}
ICP
Positional Arguments
- iterations:
integer()
Keyword Arguments
- tolerence:
float
. - rejectionScale:
float
. - numLevels:
integer()
. - sampleType:
integer()
. - numMaxCorr:
integer()
.
Return
self:
ICP
\brief ICP constructor with default arguments.
Python prototype (for reference only):
ICP(iterations[, tolerence[, rejectionScale[, numLevels[, sampleType[, numMaxCorr]]]]]) -> <ppf_match_3d_ICP object>
@spec registerModelToScene( t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in() ) :: {integer(), number(), Evision.Mat.t()} | {:error, String.t()}
registerModelToScene
Positional Arguments
- self:
Evision.PPFMatch3D.ICP.t()
- srcPC:
Evision.Mat
- dstPC:
Evision.Mat
Return
retval:
integer()
residual:
double
pose:
Evision.Mat.t()
\brief Perform registration
\details It is assumed that the model is registered on the scene. Scene remains static, while the model transforms. The output poses transform the models onto the scene. Because of the point to plane minimization, the scene is expected to have the normals available. Expected to have the normals (Nx6).
Python prototype (for reference only):
registerModelToScene(srcPC, dstPC) -> retval, residual, pose
@spec registerModelToScene( t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in(), [ Evision.PPFMatch3D.Pose3D.t() ] ) :: {integer(), [Evision.PPFMatch3D.Pose3D.t()]} | {:error, String.t()}
registerModelToScene
Positional Arguments
- self:
Evision.PPFMatch3D.ICP.t()
- srcPC:
Evision.Mat
- dstPC:
Evision.Mat
Return
retval:
integer()
poses:
[Evision.PPFMatch3D.Pose3D]
\brief Perform registration with multiple initial poses
\details It is assumed that the model is registered on the scene. Scene remains static, while the model transforms. The output poses transform the models onto the scene. Because of the point to plane minimization, the scene is expected to have the normals available. Expected to have the normals (Nx6).
Python prototype (for reference only):
registerModelToScene(srcPC, dstPC, poses) -> retval, poses