Compute Library
 19.08
NEHOGDetector Class Reference

Basic function to execute HOG detector based on linear SVM. More...

#include <NEHOGDetector.h>

Collaboration diagram for NEHOGDetector:
[legend]

Public Member Functions

void configure (const ITensor *input, const IHOG *hog, IDetectionWindowArray *detection_windows, const Size2D &detection_window_stride, float threshold=0.0f, size_t idx_class=0)
 Initialise the kernel's input, output, HOG data object, detection window stride, threshold and index class. More...
 
- Public Member Functions inherited from INESimpleFunctionNoBorder
 INESimpleFunctionNoBorder ()
 Constructor. More...
 
void run () override final
 Run the kernels contained in the function. More...
 
- Public Member Functions inherited from IFunction
virtual ~IFunction ()=default
 Destructor. More...
 
virtual void prepare ()
 Prepare the function for executing. More...
 

Detailed Description

Basic function to execute HOG detector based on linear SVM.

This function calls the following NEON kernel:

  1. NEHOGDetectorKernel

Definition at line 38 of file NEHOGDetector.h.

Member Function Documentation

◆ configure()

void configure ( const ITensor input,
const IHOG hog,
IDetectionWindowArray detection_windows,
const Size2D detection_window_stride,
float  threshold = 0.0f,
size_t  idx_class = 0 
)

Initialise the kernel's input, output, HOG data object, detection window stride, threshold and index class.

Attention
The function does not reset the number of values in IDetectionWindowArray so it is caller's responsibility to clear it.
Parameters
[in]inputInput tensor. It is the output of NEHOGDescriptor. Data type supported: F32
[in]hogHOG data-object that describes the HOG descriptor
[out]detection_windowsArray of DetectionWindow used to store the detected objects
[in]detection_window_strideDistance in pixels between 2 consecutive detection windows in x and y directions. It must be multiple of the block stride stored in hog
[in]threshold(Optional) Threshold for the distance between features and SVM classifying plane
[in]idx_class(Optional) Index of the class used for evaluating which class the detection window belongs to

Definition at line 31 of file NEHOGDetector.cpp.

32 {
33  auto k = arm_compute::support::cpp14::make_unique<NEHOGDetectorKernel>();
34  k->configure(input, hog, detection_windows, detection_window_stride, threshold, idx_class);
35  _kernel = std::move(k);
36 }
SimpleTensor< T > threshold(const SimpleTensor< T > &src, T threshold, T false_value, T true_value, ThresholdType type, T upper)
Definition: Threshold.cpp:35

References arm_compute::test::validation::reference::threshold().


The documentation for this class was generated from the following files: