Trait opencv::ximgproc::RICInterpolator[−][src]

pub trait RICInterpolator: RICInterpolatorConst + SparseMatchInterpolator {

Show 15 methods    fn as_raw_mut_RICInterpolator(&mut self) -> *mut c_void;

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

    fn set_cost_map(&mut self, cost_map: &Mat) -> Result<()> { ... }

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

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

    fn set_superpixel_ruler(&mut self, ruler: f32) -> Result<()> { ... }

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

    fn set_alpha(&mut self, alpha: f32) -> Result<()> { ... }

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

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

    fn set_max_flow(&mut self, max_flow: f32) -> Result<()> { ... }

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

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

    fn set_fgs_lambda(&mut self, lambda: f32) -> Result<()> { ... }

    fn set_fgs_sigma(&mut self, sigma: f32) -> Result<()> { ... }

}

Required methods

Provided methods

K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of Hu2017 uses 32.

C++ default parameters
  • k: 32

Interface to provide a more elaborated cost map, i.e. edge map, for the edge-aware term. This implementation is based on a rather simple gradient-based edge map estimation. To used more complex edge map estimator (e.g. StructuredEdgeDetection that has been used in the original publication) that may lead to improved accuracies, the internal edge map estimation can be bypassed here.

Parameters
  • costMap: a type CV_32FC1 Mat is required.
See also

cv::ximgproc::createSuperpixelSLIC

Get the internal cost, i.e. edge map, used for estimating the edge-aware term.

See also

setCostMap

C++ default parameters
  • sp_size: 15

Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model.

C++ default parameters
  • sp_nn: 150

Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation.

See also

cv::ximgproc::createSuperpixelSLIC

C++ default parameters
  • ruler: 15.f

Parameter to choose superpixel algorithm variant to use:

  • cv::ximgproc::SLICType SLIC segments image using a desired region_size (value: 100)
  • cv::ximgproc::SLICType SLICO will optimize using adaptive compactness factor (value: 101)
  • cv::ximgproc::SLICType MSLIC will optimize using manifold methods resulting in more content-sensitive superpixels (value: 102).
See also

cv::ximgproc::createSuperpixelSLIC

C++ default parameters
  • mode: 100

Alpha is a parameter defining a global weight for transforming geodesic distance into weight.

C++ default parameters
  • alpha: 0.7f

Parameter defining the number of iterations for piece-wise affine model estimation.

C++ default parameters
  • model_iter: 4

Parameter to choose wether additional refinement of the piece-wise affine models is employed.

C++ default parameters
  • refine_modles: true

MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead.

C++ default parameters
  • max_flow: 250.f

Parameter to choose wether the VariationalRefinement post-processing is employed.

C++ default parameters
  • use_variational_refinement: false

Sets whether the fastGlobalSmootherFilter() post-processing is employed.

C++ default parameters
  • use_fgs: true

Sets the respective fastGlobalSmootherFilter() parameter.

C++ default parameters
  • lambda: 500.f

Sets the respective fastGlobalSmootherFilter() parameter.

C++ default parameters
  • sigma: 1.5f

Implementors