The MCvFGDStatModelParams type exposes the following members.
Fields
| Name | Description | |
|---|---|---|
| alpha1 |
How quickly we forget old background pixel values seen. Typically set to 0.1
| |
| alpha2 |
"Controls speed of feature learning". Depends on T. Typical value circa 0.005.
| |
| alpha3 |
Alternate to alpha2, used (e.g.) for quicker initial convergence. Typical value 0.1.
| |
| delta |
Affects color and color co-occurrence quantization, typically set to 2.
| |
| is_obj_without_holes |
If TRUE we ignore holes within foreground blobs. Defaults to TRUE.
| |
| Lc |
Quantized levels per 'color' component. Power of two, typically 32, 64 or 128.
| |
| Lcc |
Quantized levels per 'color co-occurrence' component. Power of two, typically 16, 32 or 64.
| |
| minArea |
Discard foreground blobs whose bounding box is smaller than this threshold.
| |
| N1c |
Number of color vectors used to model normal background color variation at a given pixel.
| |
| N1cc |
Number of color co-occurrence vectors used to model normal background color variation at a given pixel.
| |
| N2c |
Number of color vectors retained at given pixel. Must be > N1c, typically ~ 5/3 of N1c.
| |
| N2cc |
Number of color co-occurrence vectors retained at given pixel. Must be > N1cc, typically ~ 5/3 of N1cc.
| |
| perform_morphing |
Number of erode-dilate-erode foreground-blob cleanup iterations.
| |
| T |
"A percentage value which determines when new features can be recognized as new background." (Typically 0.9).
|