An implementation of the alpha hull model. This methods provides more flexibility over traditional convex functions. You can adjust the alpha parameter to relax or increase the tension between boundary points. This provides the ability to create and "exact" or "generalized" envelope.

 

PROGRAM

ConvexHull

USE

CREATE CONVEX HULL USING THE Pateiro-Lopez ALPHAHULL MODEL 
 

REQUIRES

sp, alphahull, maptools
                                                                                                                                                                                                   
ARGUMENTS
      x          sp Points CLASS OBJECT                      
      alpha      CONVEX HULL ALPHA VALUE (SEE ?alphahull)
      increment  DEFAULT 360   
      rnd        DEFAULT 2

​

VALUE
     A sp SpatialPolygonsDataFrame OBJECT        

​

NOTES
   THIS METHOD PROVIDES FLEXIBILITY OVER TRADITIONAL CONVEX FUNCTIONS. YOU CAN
     ADJUST THE ALPHA PARAMETER TO RELAX OR INCREASE TENSION BETWEEN EDGE-BOUNDARY
     POINTS TO CREATE MORE OF AN EXACT FIT OF THE ENVELOPE (SEE EXAMPLE).

​

REFERENCES
    Pateiro-López & Rodríguez-Casal (2009) Generalizing the Convex Hull of a Sample: The R Package alphahull. Journal of Statistical

        Software 34(5):1-28 http://www.jstatsoft.org/v34/i05/paper
                                                                     
EXAMPLES
   require(sp)
   data(meuse)
   coordinates(meuse) = ~x+y
   a <- ConvexHull(meuse, alpha=100000)
     plot(a)
       points(meuse, pch=19)

   TEST MULTIPLE alpha VALUES
   a=c(1000, 100000)
    par(mfcol=c(1,2))
      for (alpha in a) {
     ch <- ConvexHull(meuse, alpha=alpha)
        plot(ch)
         points(meuse, pch=19)
      }