CudaHOG Class

Create a new HOGDescriptor using the specific parameters

Returns the block histogram size.

The descriptor format

Returns the number of coefficients required for the classification.

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

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

Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specfied 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.

L2-Hys normalization method shrinkage.

Maximum number of detection window increases

Pointer to the unmanaged object

Coefficient of the detection window increase.

Pointer to the shared pointer to the unmanaged object

Gaussian smoothing window parameter

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

Performs object detection with increasing detection window.

Performs object detection with a multi-scale window.

The dispose function that implements IDisposable interface

Release the unmanaged memory associated with this HOGDescriptor

Destructor

Returns coefficients of the classifier trained for people detection (for default window size).

Release the managed resources. This function will be called during the disposal of the current object. override ride this function if you need to call the Dispose() function on any managed IDisposable object created by the current object

Set the SVM detector

A pointer to the unmanaged object

A pointer to the shared pointer to the unmanaged object