Enhanced Saliency Prediction via Orientation Selectivity
Peng Ye, Yongfang Wang, Yumeng Xia · 2020
Saliency prediction can be treated as the activity of the human visual system (HVS). The most effective method should highly approximate the response of HVS to the perceived information. Motivated by that orientation selectivity (OS) mechanism occuring in primary visual cortex (PVC) tells us how the HVS extracts visual information for scene understanding, we propose a novel saliency model by combining an orientation selectivity based local feature called "excitement" map and a visual acuity based global feature called "acuity" map. Further, a saliency augmented operator based on visual error sensitivity is designed to enhance the saliency map. Experimental results on three benchmark databases demonstrate the superior performance of the proposed method compared to ten classical/ state-of-the-art algorithms.