tgrw: Interpolate using time geographic constrained random walk
In jedalong/PathInterpolatR: Methods for path interpolation

Description Usage Arguments Details Value References Examples

View source: R/tgrw.r

Perform path interpolation using the constrained random walk method outlined in the paper by Technitis et al. (2015), as implemented in the paper by Long (2015).

1	tgrw(xyt, t.slice, vmax = NA)

`xyt`	a 2x3 dataframe containing the coordinates and times of the two points to be interpolated between, often termed the anchor points of the space-prism. Each row of the dataframe should be arranged as x, y, t.
`t.slice`	a single time (POSIX or numeric), or list of times, to be interpolated for. The times must lie between those of the points in `xyt`.
`vmax`	parameter controlling the bounds of the constrained random walk. Default value is 1.5 x d/t where d is the distance between the anchor points and t the time difference.

Many moving objects exhibit movement properties that can be modelled via random walks. Thus, in many cases it is of interest to use random walks as a model for path interpolation. The time geographic constraned random walk is a special case of the random walk, wherby the interpolation is constrained by the space-time prism. The size of the space-time prism is controlled by the parameter vmax, which sets how far the interpolation is allowed to 'wander'. For more details, please see Technitis et al. (2015).

The function returns a dataframe (with nrow = length{t.slice}) corresponding to the interpolated locations.

Long, JA (2015) Kinematic interpolation of movement data. International Journal of Geographical Information Science. DOI: 10.1080/13658816.2015.1081909.

Technitis, G. et al. (2015) From A to B, randomly: A point-to-point random trajectory generator for animal movement. International Journal of Geographical Information Science. 29(6): 912-934.

data(contrived)
xyt <- contrived
###times for interpolation
t.slice <- c(1.5,2,2.5,3,3.5,4,4.5,5,5.5)
a <- tgrw(xyt[2:3,],t.slice,vmax=6)
plot(xyt[,1],xyt[,2],pch=20)
points(a[,1],a[,2])