An In Depth View of Saliency

Abstract

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.

Stereoscopic image quality assessment method based on binocular combination saliency model

“…Besides, the proposed 3D model has better overall performance than NN-OR model, which further indicates that the improved 3D saliency map has greater effect on stereoscopic image quality assessment than the original 3D saliency map in work [58]. Table 11 shows the time complexity comparison among the existed SIQA 56 30.341 models on SVBL 3D IQA Database based on the same platform above. It further indicates that the proposed model has the best overall performance than other models.…”

“…Ouerhani et al [55] took the depth feature as additional information and finally combined with 2D saliency map to obtain the 3D saliency map. Ciptadi et al [56] designed a 3D saliency detection model based on the feature of color and depth information. Wang et al [57] proposed a computational model of 3D visual saliency by merging the depth saliency map with the results of 2D visual feature detection.…”

Visual saliency detection for RGB-D images under a Bayesian framework

“…Most existing approaches for 3D saliency detection either treat the depth feature as an indicator to weight the RGB saliency map [15][16][17][18] or consider the 3D saliency map as the fusion of saliency maps of these low-level features [19][20][21][22]. It is not clear how to integrate 2D saliency features with depth-induced saliency feature in a better way, and linearly combining the saliency maps produced by these features cannot guarantee better results.…”

“…Depth-weighting models This type of model adopts depth information to weight a 2D saliency map to calculate the final saliency map for RGB-D images with feature map fusion [15][16][17][18]. Fang et al proposed a novel 3D saliency detection framework based on colour, luminance, texture, and depth contrast features, and they designed a new fusion method to combine the feature maps to obtain the final saliency map for RGB-D images [15].…”

“…In [16], colour contrast features and depth contrast features were calculated to construct an effective multi-feature fusion to generate saliency maps, and multi-scale enhancement was performed on the saliency map to further improve the detection precision, focusing on 3D salient object detection. Ciptadi et al proposed a novel computational model of visual saliency that incorporates depth information and demonstrated the method by explicitly constructing a 3D layout and shape features from depth measurements [17].…”