struct cv::cuda::FGDParams

Overview

#include <cudalegacy.hpp>

struct FGDParams
{
    // fields

    float alpha1;
    float alpha2;
    float alpha3;
    float delta;
    bool is_obj_without_holes;
    int Lc;
    int Lcc;
    float minArea;
    int N1c;
    int N1cc;
    int N2c;
    int N2cc;
    int perform_morphing;
    float T;
};

Detailed Documentation

Fields

float alpha1

How quickly we forget old background pixel values seen. Typically set to 0.1.

float alpha2

“Controls speed of feature learning”. Depends on T. Typical value circa 0.005.

float alpha3

Alternate to alpha2, used (e.g.) for quicker initial convergence. Typical value 0.1.

float delta

Affects color and color co-occurrence quantization, typically set to 2.

bool is_obj_without_holes

If TRUE we ignore holes within foreground blobs. Defaults to TRUE.

int Lc

Quantized levels per ‘color’ component. Power of two, typically 32, 64 or 128.

int Lcc

Quantized levels per ‘color co-occurrence’ component. Power of two, typically 16, 32 or 64.

float minArea

Discard foreground blobs whose bounding box is smaller than this threshold.

int N1c

Number of color vectors used to model normal background color variation at a given pixel.

int N1cc

Number of color co-occurrence vectors used to model normal background color variation at a given pixel.

int N2c

Used to allow the first N1c vectors to adapt over time to changing background.

Number of color vectors retained at given pixel. Must be > N1c, typically ~ 5/3 of N1c.

int N2cc

Used to allow the first N1cc vectors to adapt over time to changing background.

Number of color co-occurrence vectors retained at given pixel. Must be > N1cc, typically ~ 5/3 of N1cc.

int perform_morphing

These erase one-pixel junk blobs and merge almost-touching blobs. Default value is 1.

Number of erode-dilate-erode foreground-blob cleanup iterations.

float T

A percentage value which determines when new features can be recognized as new background. (Typically 0.9).