View Source Evision.CUDA.StereoBeliefPropagation (Evision v0.1.34)
Summary
Functions
Clears the algorithm state
Variant 1:
Enables the stereo correspondence operator that finds the disparity for the specified data cost.
Variant 1:
Enables the stereo correspondence operator that finds the disparity for the specified data cost.
Variant 1:
compute
Variant 1:
compute
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
Uses a heuristic method to compute the recommended parameters ( ndisp, iters and levels ) for the specified image size ( width and height ).
getBlockSize
getDataWeight
getDefaultName
getDiscSingleJump
getDisp12MaxDiff
getMaxDataTerm
getMaxDiscTerm
getMinDisparity
getMsgType
getNumDisparities
getNumIters
getNumLevels
getSpeckleRange
getSpeckleWindowSize
Reads algorithm parameters from a file storage
save
setBlockSize
setDataWeight
setDiscSingleJump
setDisp12MaxDiff
setMaxDataTerm
setMaxDiscTerm
setMinDisparity
setMsgType
setNumDisparities
setNumIters
setNumLevels
setSpeckleRange
setSpeckleWindowSize
Stores algorithm parameters in a file storage
write
Types
@type t() :: %Evision.CUDA.StereoBeliefPropagation{ref: reference()}
Type that represents an CUDA.StereoBeliefPropagation
struct.
ref.
reference()
The underlying erlang resource variable.
Functions
Clears the algorithm state
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Python prototype (for reference only):
clear() -> None
@spec compute(t(), Evision.Mat.maybe_mat_in()) :: Evision.Mat.t() | {:error, String.t()}
@spec compute(t(), Evision.CUDA.GpuMat.t()) :: Evision.CUDA.GpuMat.t() | {:error, String.t()}
Variant 1:
Enables the stereo correspondence operator that finds the disparity for the specified data cost.
Positional Arguments
self:
Evision.CUDA.StereoBeliefPropagation.t()
data:
Evision.Mat.t()
.User-specified data cost, a matrix of msg_type type and Size(\<image columns>*ndisp, \<image rows>) size.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.Stream for the asynchronous version.
Return
disparity:
Evision.Mat.t()
.Output disparity map. If disparity is empty, the output type is CV_16SC1 . Otherwise, the type is retained. In 16-bit signed format, the disparity values do not have fractional bits.
Python prototype (for reference only):
compute(data[, disparity[, stream]]) -> disparity
Variant 2:
Enables the stereo correspondence operator that finds the disparity for the specified data cost.
Positional Arguments
self:
Evision.CUDA.StereoBeliefPropagation.t()
data:
Evision.CUDA.GpuMat.t()
.User-specified data cost, a matrix of msg_type type and Size(\<image columns>*ndisp, \<image rows>) size.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.Stream for the asynchronous version.
Return
disparity:
Evision.CUDA.GpuMat.t()
.Output disparity map. If disparity is empty, the output type is CV_16SC1 . Otherwise, the type is retained. In 16-bit signed format, the disparity values do not have fractional bits.
Python prototype (for reference only):
compute(data[, disparity[, stream]]) -> disparity
@spec compute(t(), Evision.Mat.maybe_mat_in(), [{atom(), term()}, ...] | nil) :: Evision.Mat.t() | {:error, String.t()}
@spec compute(t(), Evision.CUDA.GpuMat.t(), [{atom(), term()}, ...] | nil) :: Evision.CUDA.GpuMat.t() | {:error, String.t()}
Variant 1:
Enables the stereo correspondence operator that finds the disparity for the specified data cost.
Positional Arguments
self:
Evision.CUDA.StereoBeliefPropagation.t()
data:
Evision.Mat.t()
.User-specified data cost, a matrix of msg_type type and Size(\<image columns>*ndisp, \<image rows>) size.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.Stream for the asynchronous version.
Return
disparity:
Evision.Mat.t()
.Output disparity map. If disparity is empty, the output type is CV_16SC1 . Otherwise, the type is retained. In 16-bit signed format, the disparity values do not have fractional bits.
Python prototype (for reference only):
compute(data[, disparity[, stream]]) -> disparity
Variant 2:
Enables the stereo correspondence operator that finds the disparity for the specified data cost.
Positional Arguments
self:
Evision.CUDA.StereoBeliefPropagation.t()
data:
Evision.CUDA.GpuMat.t()
.User-specified data cost, a matrix of msg_type type and Size(\<image columns>*ndisp, \<image rows>) size.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.Stream for the asynchronous version.
Return
disparity:
Evision.CUDA.GpuMat.t()
.Output disparity map. If disparity is empty, the output type is CV_16SC1 . Otherwise, the type is retained. In 16-bit signed format, the disparity values do not have fractional bits.
Python prototype (for reference only):
compute(data[, disparity[, stream]]) -> disparity
@spec compute( t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in(), Evision.CUDA.Stream.t() ) :: Evision.Mat.t() | {:error, String.t()}
@spec compute( t(), Evision.CUDA.GpuMat.t(), Evision.CUDA.GpuMat.t(), Evision.CUDA.Stream.t() ) :: Evision.CUDA.GpuMat.t() | {:error, String.t()}
Variant 1:
compute
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- left:
Evision.Mat.t()
- right:
Evision.Mat.t()
- stream:
Evision.CUDA.Stream.t()
Return
- disparity:
Evision.Mat.t()
.
Has overloading in C++
Python prototype (for reference only):
compute(left, right, stream[, disparity]) -> disparity
Variant 2:
compute
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- left:
Evision.CUDA.GpuMat.t()
- right:
Evision.CUDA.GpuMat.t()
- stream:
Evision.CUDA.Stream.t()
Return
- disparity:
Evision.CUDA.GpuMat.t()
.
Has overloading in C++
Python prototype (for reference only):
compute(left, right, stream[, disparity]) -> disparity
@spec compute( t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in(), Evision.CUDA.Stream.t(), [{atom(), term()}, ...] | nil ) :: Evision.Mat.t() | {:error, String.t()}
@spec compute( t(), Evision.CUDA.GpuMat.t(), Evision.CUDA.GpuMat.t(), Evision.CUDA.Stream.t(), [{atom(), term()}, ...] | nil ) :: Evision.CUDA.GpuMat.t() | {:error, String.t()}
Variant 1:
compute
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- left:
Evision.Mat.t()
- right:
Evision.Mat.t()
- stream:
Evision.CUDA.Stream.t()
Return
- disparity:
Evision.Mat.t()
.
Has overloading in C++
Python prototype (for reference only):
compute(left, right, stream[, disparity]) -> disparity
Variant 2:
compute
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- left:
Evision.CUDA.GpuMat.t()
- right:
Evision.CUDA.GpuMat.t()
- stream:
Evision.CUDA.Stream.t()
Return
- disparity:
Evision.CUDA.GpuMat.t()
.
Has overloading in C++
Python prototype (for reference only):
compute(left, right, stream[, disparity]) -> disparity
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
bool
Python prototype (for reference only):
empty() -> retval
@spec estimateRecommendedParams(integer(), integer(), integer(), integer(), integer()) :: :ok | {:error, String.t()}
Uses a heuristic method to compute the recommended parameters ( ndisp, iters and levels ) for the specified image size ( width and height ).
Positional Arguments
- width:
int
- height:
int
- ndisp:
int
- iters:
int
- levels:
int
Python prototype (for reference only):
estimateRecommendedParams(width, height, ndisp, iters, levels) -> None
getBlockSize
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getBlockSize() -> retval
getDataWeight
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
double
Python prototype (for reference only):
getDataWeight() -> retval
getDefaultName
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
String
Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.
Python prototype (for reference only):
getDefaultName() -> retval
getDiscSingleJump
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
double
Python prototype (for reference only):
getDiscSingleJump() -> retval
getDisp12MaxDiff
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getDisp12MaxDiff() -> retval
getMaxDataTerm
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
double
Python prototype (for reference only):
getMaxDataTerm() -> retval
getMaxDiscTerm
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
double
Python prototype (for reference only):
getMaxDiscTerm() -> retval
getMinDisparity
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getMinDisparity() -> retval
getMsgType
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getMsgType() -> retval
getNumDisparities
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getNumDisparities() -> retval
getNumIters
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getNumIters() -> retval
getNumLevels
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getNumLevels() -> retval
getSpeckleRange
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getSpeckleRange() -> retval
getSpeckleWindowSize
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
Return
- retval:
int
Python prototype (for reference only):
getSpeckleWindowSize() -> retval
@spec read(t(), Evision.FileNode.t()) :: t() | {:error, String.t()}
Reads algorithm parameters from a file storage
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- fn_:
Evision.FileNode.t()
Python prototype (for reference only):
read(fn_) -> None
save
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- filename:
String
Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).
Python prototype (for reference only):
save(filename) -> None
setBlockSize
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- blockSize:
int
Python prototype (for reference only):
setBlockSize(blockSize) -> None
setDataWeight
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- data_weight:
double
Python prototype (for reference only):
setDataWeight(data_weight) -> None
setDiscSingleJump
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- disc_single_jump:
double
Python prototype (for reference only):
setDiscSingleJump(disc_single_jump) -> None
setDisp12MaxDiff
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- disp12MaxDiff:
int
Python prototype (for reference only):
setDisp12MaxDiff(disp12MaxDiff) -> None
setMaxDataTerm
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- max_data_term:
double
Python prototype (for reference only):
setMaxDataTerm(max_data_term) -> None
setMaxDiscTerm
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- max_disc_term:
double
Python prototype (for reference only):
setMaxDiscTerm(max_disc_term) -> None
setMinDisparity
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- minDisparity:
int
Python prototype (for reference only):
setMinDisparity(minDisparity) -> None
setMsgType
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- msg_type:
int
Python prototype (for reference only):
setMsgType(msg_type) -> None
setNumDisparities
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- numDisparities:
int
Python prototype (for reference only):
setNumDisparities(numDisparities) -> None
setNumIters
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- iters:
int
Python prototype (for reference only):
setNumIters(iters) -> None
setNumLevels
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- levels:
int
Python prototype (for reference only):
setNumLevels(levels) -> None
setSpeckleRange
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- speckleRange:
int
Python prototype (for reference only):
setSpeckleRange(speckleRange) -> None
setSpeckleWindowSize
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- speckleWindowSize:
int
Python prototype (for reference only):
setSpeckleWindowSize(speckleWindowSize) -> None
@spec write(t(), Evision.FileStorage.t()) :: t() | {:error, String.t()}
Stores algorithm parameters in a file storage
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- fs:
Evision.FileStorage.t()
Python prototype (for reference only):
write(fs) -> None
@spec write(t(), Evision.FileStorage.t(), binary()) :: t() | {:error, String.t()}
write
Positional Arguments
- self:
Evision.CUDA.StereoBeliefPropagation.t()
- fs:
Evision.FileStorage.t()
- name:
String
Has overloading in C++
Python prototype (for reference only):
write(fs, name) -> None