Package gov.nih.mipav.model.algorithms

Class libdt.PatchExtractor

java.lang.Object
gov.nih.mipav.model.algorithms.libdt.PatchExtractor
Enclosing class:
libdt
class libdt.PatchExtractor extends Object
Class for extracting spatio-temporal patches (cubes) from a video (online mode). The extractor works in an "online" mode, where frames are added sequentially. When enough frames are added a true flag is returned, which indicates that new patches have been formed. Normalization of patches is handled efficiently, and access is given to the current video buffer. Also included is a function for converting a set of labels corresponding to each patche to an image. The actual patches will be in different places, depending on the normalization used: 1) norm_none --> patches are sub-videos of the buffer (vbuf); 2) norm_zm --> patches are sub-videos of the buffer (vbuf_zm); 3) norm_zmuv --> patches are local copies. Note that in some cases, the patches are just references to a sub-videos of the video buffer. Hence, it is not allowed to modify the patches. \sa PatchOptions, PatchBatchExtractor

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    Vector<Integer>
    allx
    invalid input: '<' offset to center of patch.
    Vector<Integer>
    ally
    invalid input: '<' all x-locations on step grid.
    javax.vecmath.Point3i
    coff
    invalid input: '<' value of curz that will form a new patch.
    int
    curz
    invalid input: '<' current z location of the patches (z of the first frame of the patch).
    boolean
    flag_zm
    invalid input: '<' the set of patches.
    libdt.Mat
    frame_center
    invalid input: '<' flag if vbuf_zm is used.
    libdt.Mat[]
    frame_patches
    invalid input: '<' center frame of the video buffer (reference to vbuf).
    Vector<javax.vecmath.Point2i>
    locyx
    invalid input: '<' number of columns in the video frame.
    Vector<Boolean>
    locyx_mask
    invalid input: '<' (y,x) coordinates of top-left of each patch.
    int
    locz
    invalid input: '<' patch mask depending on pixel variance.
    int
    nextz
    invalid input: '<' z location for next frame added.
    Vector<libdt.Mat[]>
    patches
    invalid input: '<' video buffer w/o mean [vrows,vcols,patopt.win.z] type=OPT_MAT_TYPE.
    libdt.PatchOptions
    patopt
    fill type for generating images from patch labels.
    libdt.Mat[]
    vbuf
    invalid input: '<' all y-locations on step grid.
    libdt.Mat[]
    vbuf_zm
    invalid input: '<' video buffer to store current frames [vrows,vcols,patopt.win.z] type=OPT_MAT_TYPE.
    int
    vcols
    invalid input: '<' options for extracting patches.
    int
    vrows
    invalid input: '<' options for extracting patches.

  • Constructor Summary

    Constructors
    Constructor
    Description
    PatchExtractor(libdt.PatchOptions patopt, int vrows, int vcols)
    invalid input: '<' center frames of the video buffer (reference to vbuf).

  • Method Summary

    Modifier and Type
    Method
    Description
    (package private) void
    getLoc()
     
    (package private) void
    reset()
     

    Methods inherited from class java.lang.Object

    clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

  • Field Details

    • patopt

      public libdt.PatchOptions patopt
      fill type for generating images from patch labels. \sa patchLabelsToImage

    • vrows

      public int vrows
      invalid input: '<' options for extracting patches.

    • vcols

      public int vcols
      invalid input: '<' options for extracting patches.

    • locyx

      public Vector<javax.vecmath.Point2i> locyx
      invalid input: '<' number of columns in the video frame.

    • locyx_mask

      public Vector<Boolean> locyx_mask
      invalid input: '<' (y,x) coordinates of top-left of each patch.

    • locz

      public int locz
      invalid input: '<' patch mask depending on pixel variance.

    • curz

      public int curz
      invalid input: '<' current z location of the patches (z of the first frame of the patch).

    • nextz

      public int nextz
      invalid input: '<' z location for next frame added.

    • coff

      public javax.vecmath.Point3i coff
      invalid input: '<' value of curz that will form a new patch.

    • allx

      public Vector<Integer> allx
      invalid input: '<' offset to center of patch.

    • ally

      public Vector<Integer> ally
      invalid input: '<' all x-locations on step grid.

    • vbuf

      public libdt.Mat[] vbuf
      invalid input: '<' all y-locations on step grid.

    • vbuf_zm

      public libdt.Mat[] vbuf_zm
      invalid input: '<' video buffer to store current frames [vrows,vcols,patopt.win.z] type=OPT_MAT_TYPE.

    • patches

      public Vector<libdt.Mat[]> patches
      invalid input: '<' video buffer w/o mean [vrows,vcols,patopt.win.z] type=OPT_MAT_TYPE.

    • flag_zm

      public boolean flag_zm
      invalid input: '<' the set of patches.

    • frame_center

      public libdt.Mat frame_center
      invalid input: '<' flag if vbuf_zm is used.

    • frame_patches

      public libdt.Mat[] frame_patches
      invalid input: '<' center frame of the video buffer (reference to vbuf).

  • Constructor Details

    • PatchExtractor

      public PatchExtractor(libdt.PatchOptions patopt, int vrows, int vcols)
      invalid input: '<' center frames of the video buffer (reference to vbuf).

  • Method Details

    • getLoc

      void getLoc()

    • reset

      void reset()