An In Depth View of Saliency

Visual saliency is a computational process that identifies important locations and structure in the visual field. Most current methods for saliency rely on cues such as color and texture while ignoring depth information, which is known to be an important saliency cue in the human cognitive system. We propose a novel computational model of visual saliency which incorporates depth information. We compare our approach to several state of the art visual saliency methods and we introduce a method for saliency based segmentation of generic objects. We demonstrate that by explicitly constructing 3D layout and shape features from depth measurements, we can obtain better performance than methods which treat the depth map as just another image channel. Our method requires no learning and can operate on scenes for which the system has no previous knowledge. We conduct object segmentation experiments on a new dataset of registered RGB-D images captured on a mobile-manipulator robot. Standard approaches to saliency use color, gradient, and intensity differences to distinguish unique regions from the rest of the visual field. We propose a novel method which incorporates depth measurements into the computation of visual saliency. Human subject studies have shown that depth is an important cue in determining salient regions in human visual processing [5, 6]. Depth measurements make it possible to separate objects which may be similar in appearance. In addition, shape information can be recovered from the depth channel and used to improve the discriminability of scene elements.