time-varying physical landscape (original video frame)

foveated landscape

saliency  landscape

foraging patches

sampled food items (interest points)

sampled gaze position

of the “foraging eye”

The Ecological Sampling model is a stochastic model of eye guidance

explaining  the variability of eye movements.  

The gaze shift mechanism is conceived as  an active random sampling  that the "foraging eye" carries out upon the visual landscape, under the constraints set by the  observable features   and the global complexity of the  landscape.    By drawing on results  reported in the foraging literature, the actual  gaze relocation is eventually driven by a stochastic differential equation whose noise source is sampled from a mixture ofalpha-stable distributions.

This way, the sampling strategy proposed here allows to mimic a fundamental property of the eye guidance mechanism:  where we choose to look next at any given moment in time is not completely deterministic,  but neither is it completely random

A preliminary attempt towards a composite sampling strategy for modelling gaze shift mechanisms has been presented in:

G. Boccignone and M. Ferraro, “The active sampling of gaze-shifts,”

in Image Analysis and Processing ICIAP 2011, ser. Lecture Notes in

Computer Science, G. Maino and G. Foresti, Eds. Springer Berlin /

Heidelberg, 2011, vol. 6978, pp. 187–196

However, that approach only conjectured a  simple  binary switch between a Gaussian   and  a Cauchy-like  walk.  While providing some promising  results, the approach  lacked of a general framework and  did not ground its assumptions on empirical analysis of eye-tracked data.

The full model is described in :

7. G.Boccignone and M. Ferraro, Ecological Sampling of Gaze Shifts
   

                IEEE Transactions on Systems Man Cybernetics - Part B

                (published on line   IEEExplore)

Code

MATLAB CODE

// SOFTWARE INSTALLATION (see README file)

To  create the software library and run the demos:

1) unpack the compressed zip file in your working directory and cd to such directory (ecosampling)

you will find the following directories:

      

        - /doc: the reference papers

        - /intpoints            function for sampling interest points

        - /protobj              functions for sampling proto-object parameters

- /Datasets:         image sequences  to be processed

- /results:         to store  results

        - /saltools:            the tools for computing saliency: for demo purposes 

                                   here you will find the 3-rd party Self-Resemblance method       

                                   by Seo and Milanfar, Journal of Vision (2009) 9(12):15, 1–27

                                   Store in this directory other salience methods you develop 

                                   or download from external sources

        - /stats:               statistics tools borrowed from various parties

- /visualization: some visualization tools

    

2) add the path to this directory and subdirectories in your Matlab environment

3) edit if you like the /config/config_simple.m script for tuning the parameters of the experiment  or just try it in the proposed configuration. Such configuration script will be useful to you  because

it holds  all settings used in all parts of the code, enabling the exact

reproduction of the experiment at some future date

4) run demo program

>> runEcologicalSampling

===============IMAGE SEQUENCES===========

A short sample sequence for demo purpose is provided with the source code in the Datasets directory (from the CNRS dataset)

Put in this directory your own video clips, as sequences of frames

  

===============DEMO PROGRAM==================

The script

            runEcologicalSampling

(1) sets the configuration script filename for setting the experiment

(2) sets the number of observers you want to simulate

2. (2)generates a scanpath on a video clip for each observer by calling the main function esGenerateScanpath()
   

===============================================

Permission to use, copy, or modify this software and its documentation

for educational and research purposes only and without fee is hereby

granted, provided that this copyright notice and the original authors'

names appear on all copies and supporting documentation.  For any

other uses of this software, in original or modified form, including

but not limited to distribution in whole or in part, specific prior

permission must be obtained from University of Milano and the

authors.  These programs shall not be used, rewritten, or adapted as

the basis of a commercial software or hardware product without first

obtaining appropriate licenses from U. of Milano.  The University

makes no representations about the suitability of this software for

any purpose.

It is provided "AS IS" without express or implied

warranty.