[−][src]Trait opencv::hub_prelude::CUDA_OpticalFlowDual_TVL1

pub trait CUDA_OpticalFlowDual_TVL1: CUDA_DenseOpticalFlow {
    pub fn as_raw_CUDA_OpticalFlowDual_TVL1(&self) -> *const c_void;

    pub fn as_raw_mut_CUDA_OpticalFlowDual_TVL1(&mut self) -> *mut c_void;

    pub fn get_tau(&self) -> Result<f64> { ... }

    pub fn set_tau(&mut self, tau: f64) -> Result<()> { ... }

    pub fn get_lambda(&self) -> Result<f64> { ... }

    pub fn set_lambda(&mut self, lambda: f64) -> Result<()> { ... }

    pub fn get_gamma(&self) -> Result<f64> { ... }

    pub fn set_gamma(&mut self, gamma: f64) -> Result<()> { ... }

    pub fn get_theta(&self) -> Result<f64> { ... }

    pub fn set_theta(&mut self, theta: f64) -> Result<()> { ... }

    pub fn get_num_scales(&self) -> Result<i32> { ... }

    pub fn set_num_scales(&mut self, nscales: i32) -> Result<()> { ... }

    pub fn get_num_warps(&self) -> Result<i32> { ... }

    pub fn set_num_warps(&mut self, warps: i32) -> Result<()> { ... }

    pub fn get_epsilon(&self) -> Result<f64> { ... }

    pub fn set_epsilon(&mut self, epsilon: f64) -> Result<()> { ... }

    pub fn get_num_iterations(&self) -> Result<i32> { ... }

    pub fn set_num_iterations(&mut self, iterations: i32) -> Result<()> { ... }

    pub fn get_scale_step(&self) -> Result<f64> { ... }

    pub fn set_scale_step(&mut self, scale_step: f64) -> Result<()> { ... }

    pub fn get_use_initial_flow(&self) -> Result<bool> { ... }

    pub fn set_use_initial_flow(&mut self, use_initial_flow: bool) -> Result<()> { ... }
}

Implementation of the Zach, Pock and Bischof Dual TV-L1 Optical Flow method.

Note: C. Zach, T. Pock and H. Bischof, "A Duality Based Approach for Realtime TV-L1 Optical Flow".

Note: Javier Sanchez, Enric Meinhardt-Llopis and Gabriele Facciolo. "TV-L1 Optical Flow Estimation".

Required methods

pub fn as_raw_CUDA_OpticalFlowDual_TVL1(&self) -> *const c_void[src]

pub fn as_raw_mut_CUDA_OpticalFlowDual_TVL1(&mut self) -> *mut c_void[src]

Loading content...

Provided methods

pub fn get_tau(&self) -> Result<f64>[src]

Time step of the numerical scheme.

pub fn set_tau(&mut self, tau: f64) -> Result<()>[src]

pub fn get_lambda(&self) -> Result<f64>[src]

Weight parameter for the data term, attachment parameter. This is the most relevant parameter, which determines the smoothness of the output. The smaller this parameter is, the smoother the solutions we obtain. It depends on the range of motions of the images, so its value should be adapted to each image sequence.

pub fn set_lambda(&mut self, lambda: f64) -> Result<()>[src]

pub fn get_gamma(&self) -> Result<f64>[src]

Weight parameter for (u - v)^2, tightness parameter. It serves as a link between the attachment and the regularization terms. In theory, it should have a small value in order to maintain both parts in correspondence. The method is stable for a large range of values of this parameter.

pub fn set_gamma(&mut self, gamma: f64) -> Result<()>[src]

pub fn get_theta(&self) -> Result<f64>[src]

parameter used for motion estimation. It adds a variable allowing for illumination variations Set this parameter to 1. if you have varying illumination. See: Chambolle et al, A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging Journal of Mathematical imaging and vision, may 2011 Vol 40 issue 1, pp 120-145

pub fn set_theta(&mut self, theta: f64) -> Result<()>[src]

pub fn get_num_scales(&self) -> Result<i32>[src]

Number of scales used to create the pyramid of images.

pub fn set_num_scales(&mut self, nscales: i32) -> Result<()>[src]

pub fn get_num_warps(&self) -> Result<i32>[src]

Number of warpings per scale. Represents the number of times that I1(x+u0) and grad( I1(x+u0) ) are computed per scale. This is a parameter that assures the stability of the method. It also affects the running time, so it is a compromise between speed and accuracy.

pub fn set_num_warps(&mut self, warps: i32) -> Result<()>[src]

pub fn get_epsilon(&self) -> Result<f64>[src]

Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time. A small value will yield more accurate solutions at the expense of a slower convergence.

pub fn set_epsilon(&mut self, epsilon: f64) -> Result<()>[src]

pub fn get_num_iterations(&self) -> Result<i32>[src]

Stopping criterion iterations number used in the numerical scheme.

pub fn set_num_iterations(&mut self, iterations: i32) -> Result<()>[src]

pub fn get_scale_step(&self) -> Result<f64>[src]

pub fn set_scale_step(&mut self, scale_step: f64) -> Result<()>[src]

pub fn get_use_initial_flow(&self) -> Result<bool>[src]

pub fn set_use_initial_flow(&mut self, use_initial_flow: bool) -> Result<()>[src]

Loading content...

Implementations

impl<'_> dyn CUDA_OpticalFlowDual_TVL1 + '_[src]

pub fn create(
    tau: f64,
    lambda: f64,
    theta: f64,
    nscales: i32,
    warps: i32,
    epsilon: f64,
    iterations: i32,
    scale_step: f64,
    gamma: f64,
    use_initial_flow: bool
) -> Result<Ptr<dyn CUDA_OpticalFlowDual_TVL1>>[src]

C++ default parameters

  • tau: 0.25
  • lambda: 0.15
  • theta: 0.3
  • nscales: 5
  • warps: 5
  • epsilon: 0.01
  • iterations: 300
  • scale_step: 0.8
  • gamma: 0.0
  • use_initial_flow: false

Implementors

Loading content...