Saliency detection aims to detect the most attractive objects in images, which has been widely used as a foundation for various multimedia applications. In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel prior. First, we generate an initial saliency map based on a color saliency map and a depth saliency map of a given RGB-D image. The...

Recent data have supported the hypothesis that, in primates, the primary visual cortex (V1) creates a saliency map from visual input. The exogenous guidance of attention is then realized by means of monosynaptic projections to the superior colliculus, which can select the most salient location as the target of a gaze shift. V1 is less prominent, or is even absent in lower vertebrates such as fi...

5th International Symposium on Visual Computing, Las Vegas, Nevada, USA, Nov 30 Dec 2, 2009 The goal of lossy image compression ought to be reducing entropy while preserving the perceptual quality of the image. Using gazetracked change detection experiments, we discover that human vision attends to one scale at a time. This evidence suggests that saliency should be treated on a per-scale basis,...

Saliency maps as visual attention computational models can reveal novel regions within a scene (as in the human visual system), which can decrease the amount of data to be processed in task specific computer vision applications. Most of the saliency computation models do not take advantage of prior spatial memory by giving priority to spatial or object based features to obtain bottom-up or top-...

In this paper, we propose a new pre-processing method for detecting road traffic sign based on visual saliency map model. Since the road traffic sign boards have dominent color contrast against environment, we consider the color opponents information with center surround difference normalization as an input feature extraction, which is effective to reduce noise influence as well as intensify th...

In this paper, we propose a trainable selective attention model that can inhibit an unwanted salient area and only focus on an interesting area in a static natural scene. The proposed model was implemented by the bottom-up saliency map model in conjunction with the modified adaptive resonance theory (ART) network model. The bottom-up saliency map model generates a salient area based on intensit...

In natural environments, humans select a subset of visual stimuli by directing their gaze to locations attended. In previous studies it has been found that at fixation points luminance-contrast is higher than average. This led to the hypothesis that luminance-contrast makes a major contribution to a saliency map of visual overt attention, consistent with a computation of stimulus saliency in ea...

Saliency maps are used to understand human attention and visual fixation. However, while very well established for static images, there is no general agreement on how to compute a saliency map of dynamic scenes. In this paper we propose a mathematically rigorous approach to this problem, including static saliency maps of each video frame for the calculation of the optical flow. Taking into acco...

Although there are some support vector machine (SVM) based methods for image segmentation, automatically and accurately segmenting objects that appeal to human perception is indeed a significant issue. One problem with these methods may be that the human visual attention is seldom taken into consideration. This paper proposes a novel visual saliency based SVM approach for automatic training dat...