CUDA_FGDParamsTrait

Trait CUDA_FGDParamsTrait 

Source
pub trait CUDA_FGDParamsTrait: CUDA_FGDParamsTraitConst {
Show 15 methods // Required method fn as_raw_mut_CUDA_FGDParams(&mut self) -> *mut c_void; // Provided methods fn set_lc(&mut self, val: i32) { ... } fn set_n1c(&mut self, val: i32) { ... } fn set_n2c(&mut self, val: i32) { ... } fn set_lcc(&mut self, val: i32) { ... } fn set_n1cc(&mut self, val: i32) { ... } fn set_n2cc(&mut self, val: i32) { ... } fn set_is_obj_without_holes(&mut self, val: bool) { ... } fn set_perform_morphing(&mut self, val: i32) { ... } fn set_alpha1(&mut self, val: f32) { ... } fn set_alpha2(&mut self, val: f32) { ... } fn set_alpha3(&mut self, val: f32) { ... } fn set_delta(&mut self, val: f32) { ... } fn set_t(&mut self, val: f32) { ... } fn set_min_area(&mut self, val: f32) { ... }
}
Expand description

Required Methods§

Provided Methods§

Source

fn set_lc(&mut self, val: i32)

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

Source

fn set_n1c(&mut self, val: i32)

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

Source

fn set_n2c(&mut self, val: 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.

Source

fn set_lcc(&mut self, val: i32)

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

Source

fn set_n1cc(&mut self, val: i32)

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

Source

fn set_n2cc(&mut self, val: 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.

Source

fn set_is_obj_without_holes(&mut self, val: bool)

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

Source

fn set_perform_morphing(&mut self, val: 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.

Source

fn set_alpha1(&mut self, val: f32)

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

Source

fn set_alpha2(&mut self, val: f32)

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

Source

fn set_alpha3(&mut self, val: f32)

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

Source

fn set_delta(&mut self, val: f32)

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

Source

fn set_t(&mut self, val: f32)

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

Source

fn set_min_area(&mut self, val: f32)

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

Implementors§