Modelling gaze shift as a constrained random walk

In this paper gaze shifts are considered as a realization of a stochastic process with non-local transition probabilities in a saliency field that represents a landscape upon which a constrained random walk is performed. The search is driven by a Langevin equation whose random term is generated by a Levy distribution, and by a Metropolis algorithm. Results of the simulations are compared with experimental data, and a notion of complexity is introduced to quantify the behavior of the system in different conditions.