Visual attention model for target search in cluttered scene

Abstract

Visual attention models generate saliency maps in which attentive regions are more distinctive with respect to remaining parts of the scene. In this work, a new model of orientation conspicuity map (OCM) is presented for the computation of saliency. The proposed method is based on the difference of the Gabor filter outputs with orthogonal orientations because vehicles are the targets for the search tasks in this study. Moreover, as another contribution, selective resolution for the input image, according to the distance of the target in the scene, is also utilized with the proposed scheme for the benefit to target search. Experimental results demonstrate that both the OCM model and selective resolution for input images yield promising results for the target search in cluttered scenes.