The MCvFGDStatModelParams type exposes the following members.
How quickly we forget old background pixel values seen. Typically set to 0.1
Controls speed of feature learning. Depends on T. Typical value circa 0.005.
Alternate to alpha2, used (e.g.) for quicker initial convergence. Typical value 0.1.
Affects color and color co-occurrence quantization, typically set to 2.
If 1 we ignore holes within foreground blobs. Defaults to 1.
Quantized levels per 'color' component. Power of two, typically 32, 64 or 128.
Quantized levels per 'color co-occurrence' component. Power of two, typically 16, 32 or 64.
Discard foreground blobs whose bounding box is smaller than this threshold. Try 15 for default
Number of color vectors used to model normal background color variation at a given pixel. Try 15 for default.
Number of color co-occurrence vectors used to model normal background color variation at a given pixel. Try 25 for default.
Number of color vectors retained at given pixel. Must be > N1c, typically ~ 5/3 of N1c.
Number of color co-occurrence vectors retained at given pixel. Must be > N1cc, typically ~ 5/3 of N1cc.
Number of erode-dilate-erode foreground-blob cleanup iterations.
A percentage value which determines when new features can be recognized as new background. (Typically 0.9).