From: Anders Sandberg (asa@nada.kth.se)
Date: Sat Feb 22 2003 - 13:08:41 MST
On Sat, Feb 22, 2003 at 11:01:55AM -0800, Michael M. Butler wrote:
>
> Let's hear it for LOS BRINISTAS OF THE SKY! Eyelevel estimates finally get
> a reasonable challenge.
Is it a Brinista anthem I hear from that passing spysat? :-)
> Bear in mind that a snapshot doesn't characterize the "churn" if any
> of the crowd. To do that well, we would need to (oppressively?) track
> ins-and-outs
> somehow.
Hmm, do you mean how much people arrive and depart? One might make an
estimate by looking at two subsequent photos and matching people (using
a color similarity + distance metric, and a fast bipartite graph optimum
matching). That would produce an estimated movement field, and one could
estimate the influx and outflux of people. If several such picture pairs
were made over time one could make even better estimates.
It is somewhat related to the algorithms used in ant tracking I sent a
few weeks back to Spike, although this does apparently scale better.
-- ----------------------------------------------------------------------- Anders Sandberg Towards Ascension! asa@nada.kth.se http://www.nada.kth.se/~asa/ GCS/M/S/O d++ -p+ c++++ !l u+ e++ m++ s+/+ n--- h+/* f+ g+ w++ t+ r+ !y
This archive was generated by hypermail 2.1.5 : Sat Feb 22 2003 - 13:08:03 MST