Object- and space-based visual attention: An integrated framework for autonomous robots

Abstract

This paper argues that the object-and spacebased modes of visual attention can be naturally integrated in a common mathematical framework. In an earlier work [1] we have proposed a mathematical model of visual attention for robotic system exploiting the knowledge of visual attention mechanism of the primates. This paper investigates on the validity of the proposed model for robotic systems through experimentation on a real robot. The paper sheds light on a number of real world issues involved with the design of visual attention system for physically embodied robots and explains how the proposed Bayesian model of visual attention addresses these issues. The object-and space-based modes of visual attention are naturally integrated in the model and is reflected in the sequential Monte Carlo implementation of the model on a real robot.

Top-down Spatial Attention for Visual Search: Novelty Detection-Tracking Using Spatial Memory with a Mobile Robot

“…On the other hand, several approaches combined the 3D data integration to color based models for saliency computation [32][33][34][35][36][37]. As stated by Wang et al [32], most of the 3D based models utilizes depth image from three perspectives [32]: i) depth weighting [33], ii) depth saliency [34], and iii) stereo vision models that compute and use disparity [35].…”

“…All the studies stated until now, they were generally space based approaches by comparing one position to another based on 2D color images or depth images for 3D models. There are few studies to utilize space and object based attention models or 3D real world space by using all three XYZ dimensions to find attentional objects [36,37]. For example, Garcia and Frintrop [37] proposed a model for attentional 3D Object Detection by using Kinect RGB-D scene, where they do combine clustered 3D data and color image saliency to create a 3D object saliency map [37].…”

Visual Attention Mechanism for a Social Robot

“…That is, it uses information that is not available in a preattentive stage, before objects are recognized [38]. Another approach following the space-and object-based integration is the one proposed by [11], which employs a Bayesian model to describe the visual attention mechanism.…”

Visual Attention for Robotic Cognition: A Survey

“…Many of the recent models perform object-based analysis for selective attention [17], [51], [52]. There are, however, only a few efforts which integrate spaceand object-based analysis in the same framework [4], [6], [7], [53].…”

“…In case of some real-time applications where the current visual input of the attention model is to be determined by the decision output of the model (i.e., the focus of attention) at the immediate past, the traditional computer vision models of visual attention faces severe limitations in a number of aspects [53]- [55]. Using a visual attention model as a component of robotic cognition is an example of such applications.…”