Trait opencv::prelude::DISOpticalFlow

source ·

pub trait DISOpticalFlow: DISOpticalFlowConst + DenseOpticalFlow {
    // Required method
    fn as_raw_mut_DISOpticalFlow(&mut self) -> *mut c_void;

    // Provided methods
    fn set_finest_scale(&mut self, val: i32) -> Result<()> { ... }
    fn set_patch_size(&mut self, val: i32) -> Result<()> { ... }
    fn set_patch_stride(&mut self, val: i32) -> Result<()> { ... }
    fn set_gradient_descent_iterations(&mut self, val: i32) -> Result<()> { ... }
    fn set_variational_refinement_iterations(&mut self, val: i32) -> Result<()> { ... }
    fn set_variational_refinement_alpha(&mut self, val: f32) -> Result<()> { ... }
    fn set_variational_refinement_delta(&mut self, val: f32) -> Result<()> { ... }
    fn set_variational_refinement_gamma(&mut self, val: f32) -> Result<()> { ... }
    fn set_use_mean_normalization(&mut self, val: bool) -> Result<()> { ... }
    fn set_use_spatial_propagation(&mut self, val: bool) -> Result<()> { ... }
}

Expand description

DIS optical flow algorithm.

This class implements the Dense Inverse Search (DIS) optical flow algorithm. More details about the algorithm can be found at Kroeger2016 . Includes three presets with preselected parameters to provide reasonable trade-off between speed and quality. However, even the slowest preset is still relatively fast, use DeepFlow if you need better quality and don’t care about speed.

This implementation includes several additional features compared to the algorithm described in the paper, including spatial propagation of flow vectors ([getUseSpatialPropagation]), as well as an option to utilize an initial flow approximation passed to [calc] (which is, essentially, temporal propagation, if the previous frame’s flow field is passed).

Required Methods§

source

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

Provided Methods§

source

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

Finest level of the Gaussian pyramid on which the flow is computed (zero level corresponds to the original image resolution). The final flow is obtained by bilinear upscaling.

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

Size of an image patch for matching (in pixels). Normally, default 8x8 patches work well enough in most cases.

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

Stride between neighbor patches. Must be less than patch size. Lower values correspond to higher flow quality.

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

Maximum number of gradient descent iterations in the patch inverse search stage. Higher values may improve quality in some cases.

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

Maximum number of gradient descent iterations in the patch inverse search stage. Higher values may improve quality in some cases.

fn set_variational_refinement_alpha(&mut self, val: f32) -> Result<()>

Weight of the smoothness term

fn set_variational_refinement_delta(&mut self, val: f32) -> Result<()>

Weight of the color constancy term

fn set_variational_refinement_gamma(&mut self, val: f32) -> Result<()>

Weight of the gradient constancy term

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

Whether to use mean-normalization of patches when computing patch distance. It is turned on by default as it typically provides a noticeable quality boost because of increased robustness to illumination variations. Turn it off if you are certain that your sequence doesn’t contain any changes in illumination.

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

Whether to use spatial propagation of good optical flow vectors. This option is turned on by default, as it tends to work better on average and can sometimes help recover from major errors introduced by the coarse-to-fine scheme employed by the DIS optical flow algorithm. Turning this option off can make the output flow field a bit smoother, however.