Publication

Abstract : In human visual systems, detection of the salient region plays an important role, as it ensures effective allocation of resources and fast processing. Though depth is an essential cue for visual saliency, it has not been well explored. This introduces a salient edge-based, region extraction model for RGB-D images. Most of the computational saliency models, reported in, produce smooth saliency maps; however, the edge information is not preserved. This paper presents a simple framework for the detection of salient edges by the preservation of the edges with high saliency scores. The final saliency map is obtained by fusion of the generated salient edge map and the RGB saliency map. Experiments are conducted over the publicly available RGB-D-2 dataset. The stability of the proposed RGB-D saliency model was assessed against standard evaluation metrics such as precision, recall, F-measure, MAE, NSS and AUC scores.