Implementation and Evaluation of a Computational Model of Attention for Computer Vision

Abstract

In the field of scene analysis for computer vision, a trade-off must be found between the quality of the results expected and the amount of computer resources allocated for each task. Using an adaptive vision system provides a more flexible solution as its analysis strategy can be changed according to the information available concerning the execution context. The authors describe how to create and evaluate a visual attention system tailored for interacting with a computer vision system so that it adapts its processing according to the interest (or salience) of each element of the scene. The authors propose a new set of constraints called ‘PAIRED’ to evaluate the adequacy of a model with respect to its different applications. The authors then justify why dynamical systems are a good choice for visual attention simulation, and we show that predator-prey models provide good properties for simulating the dynamic competition between different kinds of information. They present different results (cross-correlation, Kullback-Leibler divergence, normalized scanpath salience) that demonstrate that, in spite of being fast and highly configurable, their results are as plausible as existing models designed for high biological fidelity.