pub trait CUDA_FGDParamsTraitConst {
Show 15 methods
// Required method
fn as_raw_CUDA_FGDParams(&self) -> *const c_void;
// Provided methods
fn lc(&self) -> i32 { ... }
fn n1c(&self) -> i32 { ... }
fn n2c(&self) -> i32 { ... }
fn lcc(&self) -> i32 { ... }
fn n1cc(&self) -> i32 { ... }
fn n2cc(&self) -> i32 { ... }
fn is_obj_without_holes(&self) -> bool { ... }
fn perform_morphing(&self) -> i32 { ... }
fn alpha1(&self) -> f32 { ... }
fn alpha2(&self) -> f32 { ... }
fn alpha3(&self) -> f32 { ... }
fn delta(&self) -> f32 { ... }
fn t(&self) -> f32 { ... }
fn min_area(&self) -> f32 { ... }
}
Expand description
Constant methods for crate::cudalegacy::CUDA_FGDParams
Required Methods§
fn as_raw_CUDA_FGDParams(&self) -> *const c_void
Provided Methods§
Sourcefn lc(&self) -> i32
fn lc(&self) -> i32
Quantized levels per ‘color’ component. Power of two, typically 32, 64 or 128.
Sourcefn n1c(&self) -> i32
fn n1c(&self) -> i32
Number of color vectors used to model normal background color variation at a given pixel.
Sourcefn n2c(&self) -> i32
fn n2c(&self) -> i32
Number of color vectors retained at given pixel. Must be > N1c, typically ~ 5/3 of N1c. Used to allow the first N1c vectors to adapt over time to changing background.
Sourcefn lcc(&self) -> i32
fn lcc(&self) -> i32
Quantized levels per ‘color co-occurrence’ component. Power of two, typically 16, 32 or 64.
Sourcefn n1cc(&self) -> i32
fn n1cc(&self) -> i32
Number of color co-occurrence vectors used to model normal background color variation at a given pixel.
Sourcefn n2cc(&self) -> i32
fn n2cc(&self) -> i32
Number of color co-occurrence vectors retained at given pixel. Must be > N1cc, typically ~ 5/3 of N1cc. Used to allow the first N1cc vectors to adapt over time to changing background.
Sourcefn is_obj_without_holes(&self) -> bool
fn is_obj_without_holes(&self) -> bool
If TRUE we ignore holes within foreground blobs. Defaults to TRUE.
Sourcefn perform_morphing(&self) -> i32
fn perform_morphing(&self) -> i32
Number of erode-dilate-erode foreground-blob cleanup iterations. These erase one-pixel junk blobs and merge almost-touching blobs. Default value is 1.
Sourcefn alpha1(&self) -> f32
fn alpha1(&self) -> f32
How quickly we forget old background pixel values seen. Typically set to 0.1.
Sourcefn alpha2(&self) -> f32
fn alpha2(&self) -> f32
“Controls speed of feature learning”. Depends on T. Typical value circa 0.005.
Sourcefn alpha3(&self) -> f32
fn alpha3(&self) -> f32
Alternate to alpha2, used (e.g.) for quicker initial convergence. Typical value 0.1.