Struct opencv::rgbd::FastICPOdometry

pub struct FastICPOdometry { /* private fields */ }

A faster version of ICPOdometry which is used in KinectFusion implementation Partial list of differences:

• Works in parallel
• Written in universal intrinsics
• Filters points by angle
• Interpolates points and normals
• Doesn’t use masks or min/max depth filtering
• Doesn’t use random subsets of points
• Supports only Rt transform type
• Supports only 4-float vectors as input type

Implementations

impl FastICPOdometry

pub fn default() -> Result<FastICPOdometry>

pub fn new(
    camera_matrix: &Mat,
    max_dist_diff: f32,
    angle_threshold: f32,
    sigma_depth: f32,
    sigma_spatial: f32,
    kernel_size: i32,
    iter_counts: &Vector<i32>
) -> Result<FastICPOdometry>

Constructor.

Parameters

• cameraMatrix: Camera matrix
• maxDistDiff: Correspondences between pixels of two given frames will be filtered out if their depth difference is larger than maxDepthDiff
• angleThreshold: Correspondence will be filtered out if an angle between their normals is bigger than threshold
• sigmaDepth: Depth sigma in meters for bilateral smooth
• sigmaSpatial: Spatial sigma in pixels for bilateral smooth
• kernelSize: Kernel size in pixels for bilateral smooth
• iterCounts: Count of iterations on each pyramid level

C++ default parameters

• max_dist_diff: Odometry::DEFAULT_MAX_DEPTH_DIFF()
• angle_threshold: (float)(30.*CV_PI/180.)
• sigma_depth: 0.04f
• sigma_spatial: 4.5f
• kernel_size: 7
• iter_counts: std::vector()

pub fn create(
    camera_matrix: &Mat,
    max_dist_diff: f32,
    angle_threshold: f32,
    sigma_depth: f32,
    sigma_spatial: f32,
    kernel_size: i32,
    iter_counts: &Vector<i32>
) -> Result<Ptr<FastICPOdometry>>

C++ default parameters

• max_dist_diff: Odometry::DEFAULT_MAX_DEPTH_DIFF()
• angle_threshold: (float)(30.*CV_PI/180.)
• sigma_depth: 0.04f
• sigma_spatial: 4.5f
• kernel_size: 7
• iter_counts: std::vector()

Trait Implementations

impl AlgorithmTrait for FastICPOdometry

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

fn clear(&mut self) -> Result<()>

Clears the algorithm state

fn read(&mut self, fn_: &FileNode) -> Result<()>

Reads algorithm parameters from a file storage

impl AlgorithmTraitConst for FastICPOdometry

fn as_raw_Algorithm(&self) -> *const c_void

fn write(&self, fs: &mut FileStorage) -> Result<()>

Stores algorithm parameters in a file storage

fn write_with_name(&self, fs: &Ptr<FileStorage>, name: &str) -> Result<()>

simplified API for language bindings Stores algorithm parameters in a file storage

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

Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read

fn save(&self, filename: &str) -> Result<()>

Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

fn get_default_name(&self) -> Result<String>

Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.

impl Boxed for FastICPOdometry

unsafe fn from_raw(ptr: *mut c_void) -> Self

Wrap the specified raw pointer

fn into_raw(self) -> *mut c_void

Return an the underlying raw pointer while consuming this wrapper.

fn as_raw(&self) -> *const c_void

Return the underlying raw pointer.

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

Return the underlying mutable raw pointer

impl Drop for FastICPOdometry

fn drop(&mut self)

Executes the destructor for this type.

impl FastICPOdometryTrait for FastICPOdometry

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

fn set_camera_matrix(&mut self, val: &Mat) -> Result<()>

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

fn set_angle_threshold(&mut self, f: f32) -> Result<()>

fn set_sigma_depth(&mut self, f: f32) -> Result<()>

fn set_sigma_spatial(&mut self, f: f32) -> Result<()>

fn set_kernel_size(&mut self, f: i32) -> Result<()>

fn set_iteration_counts(&mut self, val: &Mat) -> Result<()>

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

impl FastICPOdometryTraitConst for FastICPOdometry

fn as_raw_FastICPOdometry(&self) -> *const c_void

fn prepare_frame_cache(
    &self,
    frame: &mut Ptr<OdometryFrame>,
    cache_type: i32
) -> Result<Size>

fn get_camera_matrix(&self) -> Result<Mat>

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

fn get_angle_threshold(&self) -> Result<f32>

fn get_sigma_depth(&self) -> Result<f32>

fn get_sigma_spatial(&self) -> Result<f32>

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

fn get_iteration_counts(&self) -> Result<Mat>

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

impl From<FastICPOdometry> for Algorithm

fn from(s: FastICPOdometry) -> Self

Converts to this type from the input type.

impl Odometry for FastICPOdometry

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

fn set_camera_matrix(&mut self, val: &Mat) -> Result<()>

See also

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

See also

impl OdometryConst for FastICPOdometry

fn as_raw_Odometry(&self) -> *const c_void

fn compute(
    &self,
    src_image: &Mat,
    src_depth: &Mat,
    src_mask: &Mat,
    dst_image: &Mat,
    dst_depth: &Mat,
    dst_mask: &Mat,
    rt: &mut dyn ToOutputArray,
    init_rt: &Mat
) -> Result<bool>

Method to compute a transformation from the source frame to the destination one. Some odometry algorithms do not used some data of frames (eg. ICP does not use images). In such case corresponding arguments can be set as empty Mat. The method returns true if all internal computations were possible (e.g. there were enough correspondences, system of equations has a solution, etc) and resulting transformation satisfies some test if it’s provided by the Odometry inheritor implementation (e.g. thresholds for maximum translation and rotation).

fn compute2(
    &self,
    src_frame: &mut Ptr<OdometryFrame>,
    dst_frame: &mut Ptr<OdometryFrame>,
    rt: &mut dyn ToOutputArray,
    init_rt: &Mat
) -> Result<bool>

One more method to compute a transformation from the source frame to the destination one. It is designed to save on computing the frame data (image pyramids, normals, etc.).

fn prepare_frame_cache(
    &self,
    frame: &mut Ptr<OdometryFrame>,
    cache_type: i32
) -> Result<Size>

Prepare a cache for the frame. The function checks the precomputed/passed data (throws the error if this data does not satisfy) and computes all remaining cache data needed for the frame. Returned size is a resolution of the prepared frame.

fn get_camera_matrix(&self) -> Result<Mat>

See also

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

See also

impl Send for FastICPOdometry