Struct CUDA_HOG

pub struct CUDA_HOG { /* private fields */ }

The class implements Histogram of Oriented Gradients (Dalal2005) object detector.

Note:

• An example applying the HOG descriptor for people detection can be found at opencv_source_code/samples/cpp/peopledetect.cpp
• A CUDA example applying the HOG descriptor for people detection can be found at opencv_source_code/samples/gpu/hog.cpp
• (Python) An example applying the HOG descriptor for people detection can be found at opencv_source_code/samples/python/peopledetect.py

Implementations

impl CUDA_HOG

pub fn create( win_size: Size, block_size: Size, block_stride: Size, cell_size: Size, nbins: i32, ) -> Result<Ptr<CUDA_HOG>>

Creates the HOG descriptor and detector.

Parameters

• win_size: Detection window size. Align to block size and block stride.
• block_size: Block size in pixels. Align to cell size. Only (16,16) is supported for now.
• block_stride: Block stride. It must be a multiple of cell size.
• cell_size: Cell size. Only (8, 8) is supported for now.
• nbins: Number of bins. Only 9 bins per cell are supported for now.

C++ default parameters

• win_size: Size(64,128)
• block_size: Size(16,16)
• block_stride: Size(8,8)
• cell_size: Size(8,8)
• nbins: 9

pub fn create_def() -> Result<Ptr<CUDA_HOG>>

Creates the HOG descriptor and detector.

Parameters

• win_size: Detection window size. Align to block size and block stride.
• block_size: Block size in pixels. Align to cell size. Only (16,16) is supported for now.
• block_stride: Block stride. It must be a multiple of cell size.
• cell_size: Cell size. Only (8, 8) is supported for now.
• nbins: Number of bins. Only 9 bins per cell are supported for now.

Note

This alternative version of CUDA_HOG::create function uses the following default values for its arguments:

• win_size: Size(64,128)
• block_size: Size(16,16)
• block_stride: Size(8,8)
• cell_size: Size(8,8)
• nbins: 9

Trait Implementations

impl AlgorithmTrait for CUDA_HOG

fn as_raw_mut_Algorithm(&mut self) -> *mut c_void

fn clear(&mut self) -> Result<()>

Clears the algorithm state

fn read(&mut self, fn_: &impl FileNodeTraitConst) -> Result<()>

Reads algorithm parameters from a file storage

impl AlgorithmTraitConst for CUDA_HOG

fn as_raw_Algorithm(&self) -> *const c_void

fn write(&self, fs: &mut impl FileStorageTrait) -> Result<()>

Stores algorithm parameters in a file storage

fn write_1(&self, fs: &mut impl FileStorageTrait, name: &str) -> Result<()>

Stores algorithm parameters in a file storage

fn write_with_name(&self, fs: &Ptr<FileStorage>, name: &str) -> Result<()>

@deprecated

fn write_with_name_def(&self, fs: &Ptr<FileStorage>) -> Result<()>

👎Deprecated:

Note

Deprecated: ## Note This alternative version of AlgorithmTraitConst::write_with_name function uses the following default values for its arguments:

fn empty(&self) -> Result<bool>

Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read

fn save(&self, filename: &str) -> Result<()>

Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

fn get_default_name(&self) -> Result<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.

impl Boxed for CUDA_HOG

unsafe fn from_raw(ptr: <CUDA_HOG as OpenCVFromExtern>::ExternReceive) -> Self

Wrap the specified raw pointer

fn into_raw(self) -> <CUDA_HOG as OpenCVTypeExternContainer>::ExternSendMut

Return the underlying raw pointer while consuming this wrapper.

fn as_raw(&self) -> <CUDA_HOG as OpenCVTypeExternContainer>::ExternSend

Return the underlying raw pointer.

fn as_raw_mut( &mut self, ) -> <CUDA_HOG as OpenCVTypeExternContainer>::ExternSendMut

Return the underlying mutable raw pointer

impl CUDA_HOGTrait for CUDA_HOG

fn as_raw_mut_CUDA_HOG(&mut self) -> *mut c_void

fn set_win_sigma(&mut self, win_sigma: f64) -> Result<()>

Gaussian smoothing window parameter.

fn set_l2_hys_threshold(&mut self, threshold_l2hys: f64) -> Result<()>

L2-Hys normalization method shrinkage.

fn set_gamma_correction(&mut self, gamma_correction: bool) -> Result<()>

Flag to specify whether the gamma correction preprocessing is required or not.

fn set_num_levels(&mut self, nlevels: i32) -> Result<()>

Maximum number of detection window increases.

fn set_hit_threshold(&mut self, hit_threshold: f64) -> Result<()>

Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specified in the detector coefficients (as the last free coefficient). But if the free coefficient is omitted (which is allowed), you can specify it manually here.

fn set_win_stride(&mut self, win_stride: Size) -> Result<()>

Window stride. It must be a multiple of block stride.

fn set_scale_factor(&mut self, scale0: f64) -> Result<()>

Coefficient of the detection window increase.

fn set_group_threshold(&mut self, group_threshold: i32) -> Result<()>

Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping. See groupRectangles.

fn set_descriptor_format( &mut self, descr_format: HOGDescriptor_DescriptorStorageFormat, ) -> Result<()>

Descriptor storage format:

fn set_svm_detector(&mut self, detector: &impl ToInputArray) -> Result<()>

Sets coefficients for the linear SVM classifier.

fn detect( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Point>, confidences: &mut Vector<f64>, ) -> Result<()>

Performs object detection without a multi-scale window.

fn detect_def( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Point>, ) -> Result<()>

Performs object detection without a multi-scale window.

fn detect_1( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Point>, confidences: &mut Vector<f64>, ) -> Result<()>

fn detect_without_conf( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Point>, ) -> Result<()>

Performs object detection without a multi-scale window.

fn detect_multi_scale( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Rect>, confidences: &mut Vector<f64>, ) -> Result<()>

Performs object detection with a multi-scale window.

fn detect_multi_scale_def( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Rect>, ) -> Result<()>

Performs object detection with a multi-scale window.

fn detect_multi_scale_1( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Rect>, confidences: &mut Vector<f64>, ) -> Result<()>

fn detect_multi_scale_without_conf( &mut self, img: &impl ToInputArray, found_locations: &mut Vector<Rect>, ) -> Result<()>

Performs object detection with a multi-scale window.

fn compute( &mut self, img: &impl ToInputArray, descriptors: &mut impl ToOutputArray, stream: &mut impl StreamTrait, ) -> Result<()>

Returns block descriptors computed for the whole image.

fn compute_def( &mut self, img: &impl ToInputArray, descriptors: &mut impl ToOutputArray, ) -> Result<()>

Returns block descriptors computed for the whole image.

impl CUDA_HOGTraitConst for CUDA_HOG

fn as_raw_CUDA_HOG(&self) -> *const c_void

fn get_win_sigma(&self) -> Result<f64>

fn get_l2_hys_threshold(&self) -> Result<f64>

fn get_gamma_correction(&self) -> Result<bool>

fn get_num_levels(&self) -> Result<i32>

fn get_hit_threshold(&self) -> Result<f64>

fn get_win_stride(&self) -> Result<Size>

fn get_scale_factor(&self) -> Result<f64>

fn get_group_threshold(&self) -> Result<i32>

fn get_descriptor_format(&self) -> Result<HOGDescriptor_DescriptorStorageFormat>

fn get_descriptor_size(&self) -> Result<size_t>

Returns the number of coefficients required for the classification.

fn get_block_histogram_size(&self) -> Result<size_t>

Returns the block histogram size.

fn get_default_people_detector(&self) -> Result<Mat>

Returns coefficients of the classifier trained for people detection.

impl Debug for CUDA_HOG

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Drop for CUDA_HOG

fn drop(&mut self)

Executes the destructor for this type.

impl From<CUDA_HOG> for Algorithm

fn from(s: CUDA_HOG) -> Self

Converts to this type from the input type.

impl Send for CUDA_HOG