View Source Evision.CUDA.HOG (Evision v0.2.9)
Summary
Functions
Clears the algorithm state
Variant 1:
Returns block descriptors computed for the whole image.
Variant 1:
Returns block descriptors computed for the whole image.
Creates the HOG descriptor and detector.
Creates the HOG descriptor and detector.
Variant 1:
Performs object detection without a multi-scale window.
Variant 1:
Performs object detection with a multi-scale window.
Variant 1:
Performs object detection with a multi-scale window.
Variant 1:
Performs object detection without a multi-scale window.
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
Returns the block histogram size.
getDefaultName
Returns coefficients of the classifier trained for people detection.
getDescriptorFormat
Returns the number of coefficients required for the classification.
getGammaCorrection
getGroupThreshold
getHitThreshold
getL2HysThreshold
getNumLevels
getScaleFactor
getWinSigma
getWinStride
Reads algorithm parameters from a file storage
save
setDescriptorFormat
setGammaCorrection
setGroupThreshold
setHitThreshold
setL2HysThreshold
setNumLevels
setScaleFactor
Variant 1:
Sets coefficients for the linear SVM classifier.
setWinSigma
setWinStride
Stores algorithm parameters in a file storage
write
Types
@type t() :: %Evision.CUDA.HOG{ref: reference()}
Type that represents an CUDA.HOG
struct.
ref.
reference()
The underlying erlang resource variable.
Functions
@spec clear(Keyword.t()) :: any() | {:error, String.t()}
@spec clear(t()) :: t() | {:error, String.t()}
Clears the algorithm state
Positional Arguments
- self:
Evision.CUDA.HOG.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:
Returns block descriptors computed for the whole image.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.Mat
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.CUDA stream.
Return
descriptors:
Evision.Mat.t()
.2D array of descriptors.
Python prototype (for reference only):
compute(img[, descriptors[, stream]]) -> descriptors
Variant 2:
Returns block descriptors computed for the whole image.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.CUDA.GpuMat.t()
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.CUDA stream.
Return
descriptors:
Evision.CUDA.GpuMat.t()
.2D array of descriptors.
Python prototype (for reference only):
compute(img[, descriptors[, stream]]) -> descriptors
@spec compute(t(), Evision.Mat.maybe_mat_in(), [{:stream, term()}] | nil) :: Evision.Mat.t() | {:error, String.t()}
@spec compute(t(), Evision.CUDA.GpuMat.t(), [{:stream, term()}] | nil) :: Evision.CUDA.GpuMat.t() | {:error, String.t()}
Variant 1:
Returns block descriptors computed for the whole image.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.Mat
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.CUDA stream.
Return
descriptors:
Evision.Mat.t()
.2D array of descriptors.
Python prototype (for reference only):
compute(img[, descriptors[, stream]]) -> descriptors
Variant 2:
Returns block descriptors computed for the whole image.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.CUDA.GpuMat.t()
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Keyword Arguments
stream:
Evision.CUDA.Stream.t()
.CUDA stream.
Return
descriptors:
Evision.CUDA.GpuMat.t()
.2D array of descriptors.
Python prototype (for reference only):
compute(img[, descriptors[, stream]]) -> descriptors
Creates the HOG descriptor and detector.
Keyword Arguments
win_size:
Size
.Detection window size. Align to block size and block stride.
block_size:
Size
.Block size in pixels. Align to cell size. Only (16,16) is supported for now.
block_stride:
Size
.Block stride. It must be a multiple of cell size.
cell_size:
Size
.Cell size. Only (8, 8) is supported for now.
nbins:
integer()
.Number of bins. Only 9 bins per cell are supported for now.
Return
- retval:
HOG
Python prototype (for reference only):
create([, win_size[, block_size[, block_stride[, cell_size[, nbins]]]]]) -> retval
@spec create(Keyword.t()) :: any() | {:error, String.t()}
@spec create( [ block_size: term(), block_stride: term(), cell_size: term(), nbins: term(), win_size: term() ] | nil ) :: t() | {:error, String.t()}
Creates the HOG descriptor and detector.
Keyword Arguments
win_size:
Size
.Detection window size. Align to block size and block stride.
block_size:
Size
.Block size in pixels. Align to cell size. Only (16,16) is supported for now.
block_stride:
Size
.Block stride. It must be a multiple of cell size.
cell_size:
Size
.Cell size. Only (8, 8) is supported for now.
nbins:
integer()
.Number of bins. Only 9 bins per cell are supported for now.
Return
- retval:
HOG
Python prototype (for reference only):
create([, win_size[, block_size[, block_stride[, cell_size[, nbins]]]]]) -> retval
@spec detect(t(), Evision.Mat.maybe_mat_in()) :: {[{number(), number()}], [number()]} | {:error, String.t()}
@spec detect(t(), Evision.CUDA.GpuMat.t()) :: {[{number(), number()}], [number()]} | {:error, String.t()}
Variant 1:
Performs object detection without a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.Mat
.Source image. CV_8UC1 and CV_8UC4 types are supported for now.
Return
found_locations:
[Point]
.Left-top corner points of detected objects boundaries.
confidences:
[double]
.Optional output array for confidences.
Python prototype (for reference only):
detect(img) -> found_locations, confidences
Variant 2:
Performs object detection without a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.CUDA.GpuMat.t()
.Source image. CV_8UC1 and CV_8UC4 types are supported for now.
Return
found_locations:
[Point]
.Left-top corner points of detected objects boundaries.
confidences:
[double]
.Optional output array for confidences.
Python prototype (for reference only):
detect(img) -> found_locations, confidences
@spec detectMultiScale(t(), Evision.Mat.maybe_mat_in()) :: {[{number(), number(), number(), number()}], [number()]} | {:error, String.t()}
@spec detectMultiScale(t(), Evision.CUDA.GpuMat.t()) :: {[{number(), number(), number(), number()}], [number()]} | {:error, String.t()}
Variant 1:
Performs object detection with a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.Mat
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Return
found_locations:
[Rect]
.Detected objects boundaries.
confidences:
[double]
.Optional output array for confidences.
Python prototype (for reference only):
detectMultiScale(img) -> found_locations, confidences
Variant 2:
Performs object detection with a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.CUDA.GpuMat.t()
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Return
found_locations:
[Rect]
.Detected objects boundaries.
confidences:
[double]
.Optional output array for confidences.
Python prototype (for reference only):
detectMultiScale(img) -> found_locations, confidences
@spec detectMultiScaleWithoutConf(t(), Evision.Mat.maybe_mat_in()) :: [{number(), number(), number(), number()}] | {:error, String.t()}
@spec detectMultiScaleWithoutConf(t(), Evision.CUDA.GpuMat.t()) :: [{number(), number(), number(), number()}] | {:error, String.t()}
Variant 1:
Performs object detection with a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.Mat
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Return
found_locations:
[Rect]
.Detected objects boundaries.
Python prototype (for reference only):
detectMultiScaleWithoutConf(img) -> found_locations
Variant 2:
Performs object detection with a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.CUDA.GpuMat.t()
.Source image. See cuda::HOGDescriptor::detect for type limitations.
Return
found_locations:
[Rect]
.Detected objects boundaries.
Python prototype (for reference only):
detectMultiScaleWithoutConf(img) -> found_locations
@spec detectWithoutConf(t(), Evision.Mat.maybe_mat_in()) :: [{number(), number()}] | {:error, String.t()}
@spec detectWithoutConf(t(), Evision.CUDA.GpuMat.t()) :: [{number(), number()}] | {:error, String.t()}
Variant 1:
Performs object detection without a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.Mat
.Source image. CV_8UC1 and CV_8UC4 types are supported for now.
Return
found_locations:
[Point]
.Left-top corner points of detected objects boundaries.
Python prototype (for reference only):
detectWithoutConf(img) -> found_locations
Variant 2:
Performs object detection without a multi-scale window.
Positional Arguments
self:
Evision.CUDA.HOG.t()
img:
Evision.CUDA.GpuMat.t()
.Source image. CV_8UC1 and CV_8UC4 types are supported for now.
Return
found_locations:
[Point]
.Left-top corner points of detected objects boundaries.
Python prototype (for reference only):
detectWithoutConf(img) -> found_locations
@spec empty(Keyword.t()) :: any() | {:error, String.t()}
@spec empty(t()) :: boolean() | {:error, String.t()}
Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
bool
Python prototype (for reference only):
empty() -> retval
@spec getBlockHistogramSize(Keyword.t()) :: any() | {:error, String.t()}
@spec getBlockHistogramSize(t()) :: integer() | {:error, String.t()}
Returns the block histogram size.
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
size_t
Python prototype (for reference only):
getBlockHistogramSize() -> retval
@spec getDefaultName(Keyword.t()) :: any() | {:error, String.t()}
@spec getDefaultName(t()) :: binary() | {:error, String.t()}
getDefaultName
Positional Arguments
- self:
Evision.CUDA.HOG.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
@spec getDefaultPeopleDetector(Keyword.t()) :: any() | {:error, String.t()}
@spec getDefaultPeopleDetector(t()) :: Evision.Mat.t() | {:error, String.t()}
Returns coefficients of the classifier trained for people detection.
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
Evision.Mat.t()
Python prototype (for reference only):
getDefaultPeopleDetector() -> retval
@spec getDescriptorFormat(Keyword.t()) :: any() | {:error, String.t()}
@spec getDescriptorFormat(t()) :: Evision.CUDA.HOGDescriptor_DescriptorStorageFormat.t() | {:error, String.t()}
getDescriptorFormat
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
HOGDescriptor::DescriptorStorageFormat
Python prototype (for reference only):
getDescriptorFormat() -> retval
@spec getDescriptorSize(Keyword.t()) :: any() | {:error, String.t()}
@spec getDescriptorSize(t()) :: integer() | {:error, String.t()}
Returns the number of coefficients required for the classification.
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
size_t
Python prototype (for reference only):
getDescriptorSize() -> retval
@spec getGammaCorrection(Keyword.t()) :: any() | {:error, String.t()}
@spec getGammaCorrection(t()) :: boolean() | {:error, String.t()}
getGammaCorrection
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
bool
Python prototype (for reference only):
getGammaCorrection() -> retval
@spec getGroupThreshold(Keyword.t()) :: any() | {:error, String.t()}
@spec getGroupThreshold(t()) :: integer() | {:error, String.t()}
getGroupThreshold
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
integer()
Python prototype (for reference only):
getGroupThreshold() -> retval
@spec getHitThreshold(Keyword.t()) :: any() | {:error, String.t()}
@spec getHitThreshold(t()) :: number() | {:error, String.t()}
getHitThreshold
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
double
Python prototype (for reference only):
getHitThreshold() -> retval
@spec getL2HysThreshold(Keyword.t()) :: any() | {:error, String.t()}
@spec getL2HysThreshold(t()) :: number() | {:error, String.t()}
getL2HysThreshold
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
double
Python prototype (for reference only):
getL2HysThreshold() -> retval
@spec getNumLevels(Keyword.t()) :: any() | {:error, String.t()}
@spec getNumLevels(t()) :: integer() | {:error, String.t()}
getNumLevels
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
integer()
Python prototype (for reference only):
getNumLevels() -> retval
@spec getScaleFactor(Keyword.t()) :: any() | {:error, String.t()}
@spec getScaleFactor(t()) :: number() | {:error, String.t()}
getScaleFactor
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
double
Python prototype (for reference only):
getScaleFactor() -> retval
@spec getWinSigma(Keyword.t()) :: any() | {:error, String.t()}
@spec getWinSigma(t()) :: number() | {:error, String.t()}
getWinSigma
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
double
Python prototype (for reference only):
getWinSigma() -> retval
@spec getWinStride(Keyword.t()) :: any() | {:error, String.t()}
@spec getWinStride(t()) :: {number(), number()} | {:error, String.t()}
getWinStride
Positional Arguments
- self:
Evision.CUDA.HOG.t()
Return
- retval:
Size
Python prototype (for reference only):
getWinStride() -> retval
@spec read(t(), Evision.FileNode.t()) :: t() | {:error, String.t()}
Reads algorithm parameters from a file storage
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- func:
Evision.FileNode
Python prototype (for reference only):
read(fn) -> None
save
Positional Arguments
- self:
Evision.CUDA.HOG.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
@spec setDescriptorFormat(t(), Evision.CUDA.HOGDescriptor_DescriptorStorageFormat.t()) :: t() | {:error, String.t()}
setDescriptorFormat
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- descr_format:
HOGDescriptor_DescriptorStorageFormat
Python prototype (for reference only):
setDescriptorFormat(descr_format) -> None
setGammaCorrection
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- gamma_correction:
bool
Python prototype (for reference only):
setGammaCorrection(gamma_correction) -> None
setGroupThreshold
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- group_threshold:
integer()
Python prototype (for reference only):
setGroupThreshold(group_threshold) -> None
setHitThreshold
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- hit_threshold:
double
Python prototype (for reference only):
setHitThreshold(hit_threshold) -> None
setL2HysThreshold
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- threshold_L2hys:
double
Python prototype (for reference only):
setL2HysThreshold(threshold_L2hys) -> None
setNumLevels
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- nlevels:
integer()
Python prototype (for reference only):
setNumLevels(nlevels) -> None
setScaleFactor
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- scale0:
double
Python prototype (for reference only):
setScaleFactor(scale0) -> None
@spec setSVMDetector(t(), Evision.Mat.maybe_mat_in()) :: t() | {:error, String.t()}
@spec setSVMDetector(t(), Evision.CUDA.GpuMat.t()) :: t() | {:error, String.t()}
Variant 1:
Sets coefficients for the linear SVM classifier.
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- detector:
Evision.Mat
Python prototype (for reference only):
setSVMDetector(detector) -> None
Variant 2:
Sets coefficients for the linear SVM classifier.
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- detector:
Evision.CUDA.GpuMat.t()
Python prototype (for reference only):
setSVMDetector(detector) -> None
setWinSigma
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- win_sigma:
double
Python prototype (for reference only):
setWinSigma(win_sigma) -> None
setWinStride
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- win_stride:
Size
Python prototype (for reference only):
setWinStride(win_stride) -> None
@spec write(t(), Evision.FileStorage.t()) :: t() | {:error, String.t()}
Stores algorithm parameters in a file storage
Positional Arguments
- self:
Evision.CUDA.HOG.t()
- fs:
Evision.FileStorage
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.HOG.t()
- fs:
Evision.FileStorage
- name:
String
Has overloading in C++
Python prototype (for reference only):
write(fs, name) -> None