Saccadic Predictive Vision Model with a Fovea
This addresses incremental improvements in bio-inspired vision systems for robotics or AI, focusing on object tracking.
The paper tackles the problem of emulating eye saccades in vision models by proposing an Error Saccade Model that moves the field of view to regions with highest prediction error, and finds that adding a fovea-like structure improves its ability to pursue detailed objects.
We propose a model that emulates saccades, the rapid movements of the eye, called the Error Saccade Model, based on the prediction error of the Predictive Vision Model (PVM). The Error Saccade Model carries out movements of the model's field of view to regions with the highest prediction error. Comparisons of the Error Saccade Model on Predictive Vision Models with and without a fovea show that a fovea-like structure in the input level of the PVM improves the Error Saccade Model's ability to pursue detailed objects in its view. We hypothesize that the improvement is due to poorer resolution in the periphery causing higher prediction error when an object passes, triggering a saccade to the next location.