[−][src]Trait opencv::prelude::DualTVL1OpticalFlow

pub trait DualTVL1OpticalFlow: DenseOpticalFlow {
    fn as_raw_DualTVL1OpticalFlow(&self) -> *const c_void;

    fn as_raw_mut_DualTVL1OpticalFlow(&mut self) -> *mut c_void;

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

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

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

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

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

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

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

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

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

    fn set_scales_number(&mut self, val: i32) -> Result<()> { ... }

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

    fn set_warpings_number(&mut self, val: i32) -> Result<()> { ... }

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

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

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

    fn set_inner_iterations(&mut self, val: i32) -> Result<()> { ... }

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

    fn set_outer_iterations(&mut self, val: i32) -> Result<()> { ... }

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

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

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

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

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

    fn set_median_filtering(&mut self, val: i32) -> Result<()> { ... }
}

"Dual TV L1" Optical Flow Algorithm.

The class implements the "Dual TV L1" optical flow algorithm described in Zach2007 and Javier2012 . Here are important members of the class that control the algorithm, which you can set after constructing the class instance:

  • member double tau Time step of the numerical scheme.

  • member double lambda 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.

  • member double theta 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.

  • member int nscales Number of scales used to create the pyramid of images.

  • member int warps 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.

  • member double epsilon 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.

  • member int iterations Stopping criterion iterations number used in the numerical scheme.

C. Zach, T. Pock and H. Bischof, "A Duality Based Approach for Realtime TV-L1 Optical Flow". Javier Sanchez, Enric Meinhardt-Llopis and Gabriele Facciolo. "TV-L1 Optical Flow Estimation".

Required methods

fn as_raw_DualTVL1OpticalFlow(&self) -> *const c_void

fn as_raw_mut_DualTVL1OpticalFlow(&mut self) -> *mut c_void

Loading content...

Provided methods

fn get_tau(&self) -> Result<f64>

Time step of the numerical scheme

See also

setTau

fn set_tau(&mut self, val: f64) -> Result<()>

Time step of the numerical scheme

See also

setTau getTau

fn get_lambda(&self) -> Result<f64>

Weight parameter for the data term, attachment parameter

See also

setLambda

fn set_lambda(&mut self, val: f64) -> Result<()>

Weight parameter for the data term, attachment parameter

See also

setLambda getLambda

fn get_theta(&self) -> Result<f64>

Weight parameter for (u - v)^2, tightness parameter

See also

setTheta

fn set_theta(&mut self, val: f64) -> Result<()>

Weight parameter for (u - v)^2, tightness parameter

See also

setTheta getTheta

fn get_gamma(&self) -> Result<f64>

coefficient for additional illumination variation term

See also

setGamma

fn set_gamma(&mut self, val: f64) -> Result<()>

coefficient for additional illumination variation term

See also

setGamma getGamma

fn get_scales_number(&self) -> Result<i32>

Number of scales used to create the pyramid of images

See also

setScalesNumber

fn set_scales_number(&mut self, val: i32) -> Result<()>

Number of scales used to create the pyramid of images

See also

setScalesNumber getScalesNumber

fn get_warpings_number(&self) -> Result<i32>

Number of warpings per scale

See also

setWarpingsNumber

fn set_warpings_number(&mut self, val: i32) -> Result<()>

Number of warpings per scale

See also

setWarpingsNumber getWarpingsNumber

fn get_epsilon(&self) -> Result<f64>

Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time

See also

setEpsilon

fn set_epsilon(&mut self, val: f64) -> Result<()>

Stopping criterion threshold used in the numerical scheme, which is a trade-off between precision and running time

See also

setEpsilon getEpsilon

fn get_inner_iterations(&self) -> Result<i32>

Inner iterations (between outlier filtering) used in the numerical scheme

See also

setInnerIterations

fn set_inner_iterations(&mut self, val: i32) -> Result<()>

Inner iterations (between outlier filtering) used in the numerical scheme

See also

setInnerIterations getInnerIterations

fn get_outer_iterations(&self) -> Result<i32>

Outer iterations (number of inner loops) used in the numerical scheme

See also

setOuterIterations

fn set_outer_iterations(&mut self, val: i32) -> Result<()>

Outer iterations (number of inner loops) used in the numerical scheme

See also

setOuterIterations getOuterIterations

fn get_use_initial_flow(&self) -> Result<bool>

Use initial flow

See also

setUseInitialFlow

fn set_use_initial_flow(&mut self, val: bool) -> Result<()>

Use initial flow

See also

setUseInitialFlow getUseInitialFlow

fn get_scale_step(&self) -> Result<f64>

Step between scales (<1)

See also

setScaleStep

fn set_scale_step(&mut self, val: f64) -> Result<()>

Step between scales (<1)

See also

setScaleStep getScaleStep

fn get_median_filtering(&self) -> Result<i32>

Median filter kernel size (1 = no filter) (3 or 5)

See also

setMedianFiltering

fn set_median_filtering(&mut self, val: i32) -> Result<()>

Median filter kernel size (1 = no filter) (3 or 5)

See also

setMedianFiltering getMedianFiltering

Loading content...

Implementations

impl<'_> dyn DualTVL1OpticalFlow + '_[src]

pub fn create(
    tau: f64,
    lambda: f64,
    theta: f64,
    nscales: i32,
    warps: i32,
    epsilon: f64,
    innner_iterations: i32,
    outer_iterations: i32,
    scale_step: f64,
    gamma: f64,
    median_filtering: i32,
    use_initial_flow: bool
) -> Result<Ptr<dyn DualTVL1OpticalFlow>>[src]

Creates instance of cv::DualTVL1OpticalFlow

C++ default parameters

  • tau: 0.25
  • lambda: 0.15
  • theta: 0.3
  • nscales: 5
  • warps: 5
  • epsilon: 0.01
  • innner_iterations: 30
  • outer_iterations: 10
  • scale_step: 0.8
  • gamma: 0.0
  • median_filtering: 5
  • use_initial_flow: false

Implementors

Loading content...