Automatic Representation and Segmentation of Video Sequences via a Novel Framework Based on the D-EVM and Kohonen Networks

Algorithm 4

Computing the () adjacencies, shared () cells, between the hypervoxels that originally defined to a given D-OPP .

   Input: A D-EVM and the number of dimensions .

   Output: The number of internal contacts perpendicular to -axis.

(1)  Procedure  InternalContacts  (D-EVM , )

(2)      EVM couplet, currentSection, previousSection;

(3)      EVM sectionInt; // Intersection result

(4)      integer 1, 2; // Couplets coordinates

(5)      integer nCoords;

(6)      integer ; // Total internal contacts

(7)      previousSection  InitEVM ( );

(8)      1  getCoord ();

(9)      couplet  readCouplet ();

(10)    while  !endEVM ()  do

              // Internal contacts for the current slice

(11)            currentSection  getSection (previousSection, couplet);

(12)             2  getCoord (p);

(13)             ;

(14)            ic  ic + Coords  Content (currentSection, );

              // Internal contacts between consecutive slices

(15)            sectionInt  BooleanOperation (previousSection, currentSection, , );

(16)            ic  ic + Content (sectionInt, );

(17)             ;

(18)             ;

(19)            couplet  readCouplet ();

(20)    return ic