Package boofcv.abst.fiducial

Class SquareBase_to_FiducialDetector<T extends ImageGray<T>,Detector extends BaseDetectFiducialSquare<T>>

java.lang.Object
boofcv.abst.fiducial.FiducialDetectorPnP<T>
boofcv.abst.fiducial.SquareBase_to_FiducialDetector<T,Detector>
All Implemented Interfaces:
FiducialDetector<T>
Direct Known Subclasses:
SquareBinary_to_FiducialDetector, SquareHamming_to_FiducialDetector, SquareImage_to_FiducialDetector
public abstract class SquareBase_to_FiducialDetector<T extends ImageGray<T>,Detector extends BaseDetectFiducialSquare<T>> extends FiducialDetectorPnP<T>
Wrapper around BaseDetectFiducialSquare for FiducialDetector

  • Constructor Details

    • SquareBase_to_FiducialDetector

      protected SquareBase_to_FiducialDetector(Detector alg)

  • Method Details

    • detect

      public void detect(T input)
      Description copied from interface: FiducialDetector
      Detects fiducials inside the image. Each call to this function only depends upon the input image. The previous calls do not affect it's outcome.
      Parameters:
      input - Input image. Not modified.

    • getCenter

      public void getCenter(int which, Point2D_F64 location)
      Return the intersection of two lines defined by opposing corners. This should also be the geometric center
      Parameters:
      which - Fiducial's index
      location - (output) Storage for the transform. modified.

    • estimatePose

      protected boolean estimatePose(int which, List<Point2D3D> points, Se3_F64 fiducialToCamera)
      Description copied from class: FiducialDetectorPnP
      Given the mapping of 2D observations to known 3D points estimate the pose of the fiducial. This solves the P-n-P problem. Do a simple form of robust estimation. Prune points which are greater than 3 standard deviations and likely noise the recompute the pose
      Overrides:
      estimatePose in class FiducialDetectorPnP<T extends ImageGray<T>>

    • setLensDistortion

      public void setLensDistortion(@Nullable @Nullable LensDistortionNarrowFOV distortion, int width, int height)
      Description copied from interface: FiducialDetector
      Specifies how to remove lens distortion from the input image and how to convert pixels into normalized image coordinates.
      Specified by:
      setLensDistortion in interface FiducialDetector<T extends ImageGray<T>>
      Overrides:
      setLensDistortion in class FiducialDetectorPnP<T extends ImageGray<T>>
      Parameters:
      distortion - Lens distortion model. null if you want to remove a lens distortion model that had previously been set.
      width - Input image's width.
      height - Input image's height

    • totalFound

      public int totalFound()
      Description copied from interface: FiducialDetector
      The total number of fiducial found
      Returns:
      number of targets found

    • getId

      public long getId(int which)
      Description copied from interface: FiducialDetector
      If applicable, returns the ID of the fiducial found. Call FiducialDetector.hasID() to see if this function returns a valid value.
      Parameters:
      which - Detected fiducial's index
      Returns:
      ID of the fiducial

    • getMessage

      public String getMessage(int which)
      Description copied from interface: FiducialDetector
      If applicable, returns a message associated with the fiducial. Call FiducialDetector.hasMessage() ()} to see if this function returns a valid value.
      Parameters:
      which - Detected fiducial's index
      Returns:
      Encoded message

    • hasID

      public boolean hasID()
      Description copied from interface: FiducialDetector
      If true then FiducialDetector.getId(int) returns a valid unique number
      Returns:
      boolean

    • hasMessage

      public boolean hasMessage()
      Description copied from interface: FiducialDetector
      If true then FiducialDetector.getMessage(int) returns a valid message
      Returns:
      boolean

    • getInputType

      public ImageType<T> getInputType()
      Description copied from interface: FiducialDetector
      Type of input image

    • getAlgorithm

      public Detector getAlgorithm()

    • getDetectedControl

      public List<PointIndex2D_F64> getDetectedControl(int which)
      Description copied from class: FiducialDetectorPnP
      Returns a list of detected control points in the image for the specified fiducial. Observations will be in distorted image pixels.
      Specified by:
      getDetectedControl in class FiducialDetectorPnP<T extends ImageGray<T>>

    • getControl3D

      protected List<Point2D3D> getControl3D(int which)
      Description copied from class: FiducialDetectorPnP
      3D location of control points in the fiducial reference frame
      Specified by:
      getControl3D in class FiducialDetectorPnP<T extends ImageGray<T>>
      Returns:
      3D location of control points

    • getBounds

      public Polygon2D_F64 getBounds(int which, @Nullable @Nullable Polygon2D_F64 storage)
      Description copied from interface: FiducialDetector
      Used to retrieve the bounds around a marker in the image. How the bounds are defined is left up the implementation. It could be a simple rectangle or it could be corner features.
      Parameters:
      which - Which fiducial.
      storage - (Optional) Storage for fiducials.
      Returns:
      Found marker. Points are owned by the caller and will not be modified in the future.