[R-sig-Geo] Spatial clustering of points within a given line

[Julius Tesoro]

Thanks for that. Is the distance of the point to this  'line segment' perpendicular?

Also, is there a package where you can do automated spatial clustering?
 

--- On Mon, 9/14/09, Adrian.Baddeley at csiro.au <Adrian.Baddeley at csiro.au> wrote:

> From: Adrian.Baddeley at csiro.au <Adrian.Baddeley at csiro.au>
> Subject: Spatial clustering of points within a given line
> To: r-sig-geo at stat.math.ethz.ch
> Cc: jutesoro at yahoo.com, Adrian.Baddeley at csiro.au, r.turner at auckland.ac.nz
> Date: Monday, September 14, 2009, 3:14 PM
> Julius Tesoro <jutesoro at yahoo.com>
> writes:
> 
> > I have a dilemma, Considering I have a number of
> points and a line (shapefile). How do > I compute for the
> shortest distance between a line and a point? 
> 
> In package 'spatstat' you would use 
>            nncross(X,Y)
> or 
>        
>    project2segment(X, Y) 
> where X is a point pattern (class "ppp") and Y is a line
> segment pattern (class "psp"). This computes the shortest
> distance from each point to the nearest line segment,
> identifies which line segment is closest to each point, and
> projects each point in X to a point on the nearest line
> segment. To convert your shapefile data to spatstat data,
> see the vignette supplied with the spatstat package.
> 
> > Also how do you identify which points aggregate near
> the line 
> > like in spatial clustering?
> 
> I'm not sure exactly what you want to do.. You could simply
> select all points whose distance to the nearest line segment
> is smaller than a certain threshold. 
> 
> regards
> Adrian Baddeley
> 
>