A proto-object based saliency model in three-dimensional space

The influence of stereopsis on visual saliency in a proto-object based model of selective attention

Some animals including humans use stereoscopic vision which reconstructs spatial information about the environment from the disparity between images captured by eyes in two separate adjacent locations. Like other sensory information, such stereoscopic information is expected to influence attentional selection. We develop a biologically plausible model of binocular vision to study its effect on bottom-up visual attention, i.e., visual saliency. In our model, the scene is organized in terms of proto-objects on which attention acts, rather than on unbound sets of elementary features. We show that taking into account the stereoscopic information improves the performance of the model in the prediction of human eye movements with statistically significant differences.

Event-driven proto-object based saliency in 3D space to attract a robot's attention

To interact with its environment, a robot working in 3D space needs to organise its visual input in terms of objects or their perceptual precursors, proto-objects. Among other visual cues, depth is a submodality used to direct attention to visual features and objects. Current depth-based proto-object attention models have been implemented for standard RGB-D cameras that produce synchronous frames. In contrast, event cameras are neuromorphic sensors that loosely mimic the function of the human retina by asynchronously encoding per-pixel brightness changes at very high temporal resolution, thereby providing advantages like high dynamic range, efficiency (thanks to their high degree of signal compression), and low latency. We propose a bio-inspired bottom-up attention model that exploits event-driven sensing to generate depth-based saliency maps that allow a robot to interact with complex visual input. We use event-cameras mounted in the eyes of the iCub humanoid robot to directly extract edge, disparity and motion information. Real-world experiments demonstrate that our system robustly selects salient objects near the robot in the presence of clutter and dynamic scene changes, for the benefit of downstream applications like object segmentation, tracking and robot interaction with external objects.

Egocentric Distance Perception Disorder in Amblyopia

Egocentric distance perception is a psychological process in which observers use various depth cues to estimate the distance between a target and themselves. The impairment of basic visual function and treatment of amblyopia have been well documented. However, the disorder of egocentric distance perception of amblyopes is poorly understood. In this review, we describe the cognitive mechanism of egocentric distance perception, and then, we focus on empirical evidence for disorders in egocentric distance perception for amblyopes in the whole visual space. In the personal space (within 2 m), it is difficult for amblyopes to show normal hand-eye coordination; in the action space (within 2 m~30 m), amblyopes cannot accurately judge the distance of a target suspended in the air. Few studies have focused on the performance of amblyopes in the vista space (more than 30 m). Finally, five critical topics for future research are discussed: 1) it is necessary to systematically explore the mechanism of egocentric distance perception in all three spaces; 2) the laws of egocentric distance perception in moving objects for amblyopes should be explored; and 3) the comparison of three subtypes of amblyopia is still insufficient; 4) study the perception of distance under another theoretical framework; 5) explore the mechanisms of amblyopia by Virtual Reality.

A Neuromorphic Proto-Object Based Dynamic Visual Saliency Model With a Hybrid FPGA Implementation

Computing and attending to salient regions of a visual scene is an innate and necessary preprocessing step for both biological and engineered systems performing high-level visual tasks including object detection, tracking, and classification. Computational bandwidth and speed are improved by preferentially devoting computational resources to salient regions of the visual field. The human brain computes saliency effortlessly, but modeling this task in engineered systems is challenging. We first present a neuromorphic dynamic saliency model, which is bottom-up, feed-forward, and based on the notion of proto-objects with neurophysiological spatio-temporal features requiring no training. Our neuromorphic model outperforms state-of-the-art dynamic visual saliency models in predicting human eye fixations (i.e., ground truth saliency). Secondly, we present a hybrid FPGA implementation of the model for real-time applications, capable of processing 112×84 resolution frames at 18.71 Hz running at a 100 MHz clock rate - a 23.77× speedup from the software implementation. Additionally, our fixed-point model of the FPGA implementation yields comparable results to the software implementation.

Analysis of spiking synchrony in visual cortex reveals distinct types of top-down modulation signals for spatial and object-based attention

The activity of a border ownership selective (BOS) neuron indicates where a foreground object is located relative to its (classical) receptive field (RF). A population of BOS neurons thus provides an important component of perceptual grouping, the organization of the visual scene into objects. In previous theoretical work, it has been suggested that this grouping mechanism is implemented by a population of dedicated grouping (“G”) cells that integrate the activity of the distributed feature cells representing an object and, by feedback, modulate the same cells, thus making them border ownership selective. The feedback modulation by G cells is thought to also provide the mechanism for object-based attention. A recent modeling study showed that modulatory common feedback, implemented by synapses with N-methyl-D-aspartate (NMDA)-type glutamate receptors, accounts for the experimentally observed synchrony in spike trains of BOS neurons and the shape of cross-correlations between them, including its dependence on the attentional state. However, that study was limited to pairs of BOS neurons with consistent border ownership preferences, defined as two neurons tuned to respond to the same visual object, in which attention decreases synchrony. But attention has also been shown to increase synchrony in neurons with inconsistent border ownership selectivity. Here we extend the computational model from the previous study to fully understand these effects of attention. We postulate the existence of a second type of G-cell that represents spatial attention by modulating the activity of all BOS cells in a spatially defined area. Simulations of this model show that a combination of spatial and object-based mechanisms fully accounts for the observed pattern of synchrony between BOS neurons. Our results suggest that modulatory feedback from G-cells may underlie both spatial and object-based attention.

Vision allows us to make sense out of a very complex signal, the patterns of light rays reaching our eyes. Two mechanisms are essential for this: perceptual organization which structures the input into meaningful visual objects, and attention which selects only the most important parts in the input. Prior work suggests that both of these mechanisms are implemented by neurons called grouping cells. These organize the object features into coherent entities (perceptual grouping) and access them as needed (selective attention). For technical reasons it is difficult to observe grouping cells but their effect can be seen in the influence they have on responses of other classes of cells. These responses have been measured experimentally and it was found that they depend in unexpected ways on where the subject was attending. Using a computational model, we here demonstrate that the responses can be understood in terms of the interaction between two kinds of selective attention, both of which are known to occur in primate perception. One is attention to a specific area in the environment, the other is to specific objects. A model including both of these attentional mechanisms generates neuronal responses in agreement with the observed patterns of neural activity.

Proto-Object Based Saliency Model With Texture Detection Channel

The amount of visual information projected from the retina to the brain exceeds the information processing capacity of the latter. Attention, therefore, functions as a filter to highlight important information at multiple stages of the visual pathway that requires further and more detailed analysis. Among other functions, this determines where to fixate since only the fovea allows for high resolution imaging. Visual saliency modeling, i.e. understanding how the brain selects important information to analyze further and to determine where to fixate next, is an important research topic in computational neuroscience and computer vision. Most existing bottom-up saliency models use low-level features such as intensity and color, while some models employ high-level features, like faces. However, little consideration has been given to mid-level features, such as texture, for visual saliency models. In this paper, we extend a biologically plausible proto-object based saliency model by adding simple texture channels which employ nonlinear operations that mimic the processing performed by primate visual cortex. The extended model shows statistically significant improved performance in predicting human fixations compared to the previous model. Comparing the performance of our model with others on publicly available benchmarking datasets, we find that our biologically plausible model matches the performance of other models, even though those were designed entirely for maximal performance with little regard to biological realism.

Learning to Explore Saliency for Stereoscopic Videos via Component-Based Interaction

In this paper, we devise a saliency prediction model for stereoscopic videos that learns to explore saliency inspired by the component-based interactions including spatial, temporal, as well as depth cues. The model first takes advantage of specific structure of 3D residual network (3D-ResNet) to model the saliency driven by spatio-temporal coherence from consecutive frames. Subsequently, the saliency inferred by implicit-depth is automatically derived based on the displacement correlation between left and right views by leveraging a deep convolutional network (ConvNet). Finally, a component-wise refinement network is devised to produce final saliency maps over time by aggregating saliency distributions obtained from multiple components. In order to further facilitate research towards stereoscopic video saliency, we create a new dataset including 175 stereoscopic video sequences with diverse content, as well as their dense eye fixation annotations. Extensive experiments support that our proposed model can achieve superior performance compared to the state-of-the-art methods on all publicly available eye fixation datasets.

Biologically-Inspired Computational Neural Mechanism for Human Action/activity Recognition: A Review

Theoretical neuroscience investigation shows valuable information on the mechanism for recognizing the biological movements in the mammalian visual system. This involves many different fields of researches such as psychological, neurophysiology, neuro-psychological, computer vision, and artificial intelligence (AI). The research on these areas provided massive information and plausible computational models. Here, a review on this subject is presented. This paper describes different perspective to look at this task including action perception, computational and knowledge based modeling, psychological, and neuroscience approaches.

Unique objects attract attention even when faint

Locally contrasting objects, e.g. a red apple surrounded by green apples, attract attention. Does this generalize to differences in feature space? That is, do unique objects-regardless of their location-stand out from a collection of objects that are similar to one another, even when the unique object has lower local contrast with the background than the other objects? Behavioral data show indeed a preference for unique items but previous experiments enabled viewers to anticipate what response they were "supposed" to give. We developed a new experimental paradigm that minimizes such top-down effects. Pitting local contrast against global uniqueness, we show that unique stimuli attract attention even in not-anticipated, never-seen images, and even when the unique stimuli are faint (low contrast). A computational model explains how competition between objects in feature space favors dissimilar objects over those with similar features. The model explains how humans select unique objects, without a loss of performance on natural scenes.

Saliency model based on a neural population for integrating figure direction and organizing Border Ownership

Attentional selection is a function of the brain that allocates computational resources momentarily to the most important part of a visual scene. Saliency map models have been used to predict the location of attentional selection and gaze. Border Ownership (BO) indicates the direction of the figure with respect to the border. I here propose a biologically plausible saliency model based on neural population for integrating the activities of intermediate-level visual areas with neurons selective to BO. A variety of BO organizations produces a population of model neurons that represent the grouping structure. In the model I propose, the interactions and the population responses of these model neurons underlie the determination of saliency and the accurate prediction of gaze location. I tested 100 patterns for BO organizations and found that the proposed saliency model not only reproduced the characteristics of perceptual organization but also captured object locations in natural images. Furthermore, the saliency model based on the population responses of the BO organization significantly improved the gaze prediction accuracy compared with previous saliency-based models. These results suggest a crucial role for a wide variety of BO organizations and neural population coding to determine saliency mediating attentional selection and to predict gaze location.

Interactions Elicited by the Contradiction Between Figure Direction Discrimination and Figure-Ground Segregation

Figure-ground (FG) segregation that separates an object from the rest of the image is a fundamental problem in vision science. A majority of neurons in monkey V2 showed the selectivity to border ownership (BO) that indicates which side of a contour owns the border. Although BO could be a precursor of FG segregation, the contribution of BO to FG segregation has not been clarified. Because FG segregation is the perception of the global region that belongs to an object, whereas BO determination provides the local direction of figure (DOF) along a contour, a spatial integration of BO might be expected for the generation of FG. To understand the mechanisms underlying the perception of figural regions, we investigated the interaction between the local BO determination and the global FG segregation through the quantitative analysis of the visual perception and the spatiotemporal characteristics of eye movements. We generated a set of novel stimuli in which translucency induces local DOF along the contour and global FG independently so that DOF and FG could be either consistent or contradictory. The perceptual responses showed better performance in DOF discrimination than FG segregation, supporting distinct mechanisms for the DOF discrimination and the FG segregation. We examined whether the contradiction between DOF and FG modulates the eye movement while participants judged DOF and FG. The duration of the first eye fixation was modulated by the contradiction during FG segregation but not DOF discrimination, suggesting a sequential processing from the BO determination to the FG segregation. These results of human perception and eye fixation provide important clues for understanding the visual processing for FG segregation.

Visual Attention Modeling for Stereoscopic Video: A Benchmark and Computational Model

In this paper, we investigate the visual attention modeling for stereoscopic video from the following two aspects. First, we build one large-scale eye tracking database as the benchmark of visual attention modeling for stereoscopic video. The database includes 47 video sequences and their corresponding eye fixation data. Second, we propose a novel computational model of visual attention for stereoscopic video based on Gestalt theory. In the proposed model, we extract the low-level features, including luminance, color, texture, and depth, from discrete cosine transform coefficients, which are used to calculate feature contrast for the spatial saliency computation. The temporal saliency is calculated by the motion contrast from the planar and depth motion features in the stereoscopic video sequences. The final saliency is estimated by fusing the spatial and temporal saliency with uncertainty weighting, which is estimated by the laws of proximity, continuity, and common fate in Gestalt theory. Experimental results show that the proposed method outperforms the state-of-the-art stereoscopic video saliency detection models on our built large-scale eye tracking database and one other database (DML-ITRACK-3D).