Basic function to execute HOG detector based on linear SVM.
More...
#include <NEHOGDetector.h>
Basic function to execute HOG detector based on linear SVM.
This function calls the following Neon kernel:
- NEHOGDetectorKernel
- Deprecated:
- This function is deprecated and is intended to be removed in 21.05 release
Definition at line 42 of file NEHOGDetector.h.
◆ NEHOGDetector() [1/3]
◆ NEHOGDetector() [2/3]
Prevent instances of this class from being copied.
◆ NEHOGDetector() [3/3]
Default move constructor.
◆ ~NEHOGDetector()
◆ configure()
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] | input | Input tensor. It is the output of NEHOGDescriptor. Data type supported: F32 |
[in] | hog | HOG data-object that describes the HOG descriptor |
[out] | detection_windows | Array of DetectionWindow used to store the detected objects |
[in] | detection_window_stride | Distance 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 32 of file NEHOGDetector.cpp.
34 auto k = std::make_unique<NEHOGDetectorKernel>();
35 k->configure(
input, hog, detection_windows, detection_window_stride,
threshold, idx_class);
36 _kernel = std::move(k);
SimpleTensor< T > threshold(const SimpleTensor< T > &src, T threshold, T false_value, T true_value, ThresholdType type, T upper)
◆ operator=() [1/2]
Prevent instances of this class from being copied.
◆ operator=() [2/2]
Default move assignment operator.
The documentation for this class was generated from the following files: