Visual scanpaths via Constrained Levy Exploration of a saliency landscape

The code is a simple demo of visual scanpath generation via Constrained Levy Exploration.

The general idea is modelling the eye-movement exploration of a saliency landscape computed from an image as the exploration of a random walking forager. The resulting foraging walk is the saccadic scanpath.

The code allows to run an experiment that puts into action a defined number of artificial observers, each generating a visual scanpath (a sequence of fixations and saccades) on a given image using a slightly enhanced version of the CLE method described in the paper:

[1] G. Boccignone and M. Ferraro, Modelling gaze shift as a constrained random walk, Physica A, vol. 331, no. 1, pp. 207-218, 2004

Enhancements concern;
- 1) Possibility of using more general alpha-stable
distributions [2] rather then stick to the Cauchy
distribution as in [1]
- 2) An informed strategy is employed to sample the
next gaze shift in that the choice of the next gaze location is
obtained through an internal simulation step: a number n of candidates gaze
shifts is preliminarly sampled and evaluated against a gain function [2].
The best among n candidate shift is eventually retained .

====SW INSTALLATION==========================================

To create the software library and run the demos:

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

you will find the following directories:
- /config: Holds the configuration script all settings used in all parts of the code, enabling the exact
reproduction of the experiment at some future date
- /doc: the reference papers
- /img: color images to be processed
- /results: to store segmentation results
- /saltools: the tools for computing saliency: for demo purposes
here you will find the Spectral Residual method
Store in this directory the methods you develop or download from external sources
- /stats: statistics tools
- /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

4) run demo program
>> runExperimentCLE

See the README.txt file for more details

===============IMAGES=========================================
Some sample images are provided with the source code in the img directory

===============DEMO PROGRAM======================================
The script

runExperimentCLE

(1) sets the configuration script filename for setting the experiment
(2) sets the number of observers you want to simulate
(2) generates a scanpath for each observer