results in: http://youtu.be/uYeWTaKyOKs
In order to run this code you need two things, 
first: You need to install and set up the Matlab libSVM library.
second: you need some images (maybe from a street video, I use the KUL video)
Change these lines:
aviobj = avifile('video_KUL.avi','FPS',8,'compression','Indeo5');
directory = '.\KUL-seq01';        %Images folder
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Also the images_dir = '.\ModelsRecognition'; directory contains the signs models for plotting them 
after the recognition (and therefore see what is the recognized sign)

This code were developed by O. Motto, I. Alonso and M. Pousa for the MCVAI Computer Vision class