earticle

영어

This work proposes a novel biologically motivated visual selective attention model for efficient visual searching, which is implemented by integrating three attention mechanisms: bottom-up attention, top-down attention, and spatial attention. Bottom-up attention generates salient locations by reflecting top-down biases as well as three primitive visual features: intensity, edge and color. Prototype-based object perception is proposed for top-down attention, in which a 3-D color histogram is applied to generate a prototype of the target object. And experience based spatial attention can determine acceleration to localize a target object, which is modeled by using memorized spatial location information updated by object-localization experience. In order to verify the performance of the proposed visual selective attention model, we apply the proposed model to a real application in pedestrian traffic signal detection, to be utilized as part of a blind guide system. The proposed selective attention model shows plausible performance in terms of accuracy and computation time while efficiently localizing pedestrian traffic signals.