Data- and model-driven gaze control for an active-vision system

Backer, Gerriet; Mertsching, Bärbel; Bollmann, Maik

doi:10.1109/34.977565

Cited by 94 publications

(41 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the paradigm of computational visual attention has been widely investigated during the last two decades. Numerous computational models have been therefore reported [8,9,10,11,12]. Most of these models rely on the feature integration theory presented by Treisman et al in [13].…”

Section: Introductionmentioning

confidence: 99%

Empirical Validation of the Saliency-based Model of Visual Attention

Ouerhani¹,

Wartburg²,

Hügli³

et al. 2003

ELCVIA

120

View full text Add to dashboard Cite

Visual attention is the ability of the human vision system to detect salient parts of the scene, on which higher vision tasks, such as recognition, can focus. In human vision, it is believed that visual attention is intimately linked to the eye movements and that the fixation points correspond to the location of the salient scene parts. In computer vision, the paradigm of visual attention has been widely investigated and a saliencybased model of visual attention is now available that is commonly accepted and used in the field, despite the fact that its biological grounding has not been fully assessed. This work proposes a new method for quantitatively assessing the plausibility of this model by comparing its performance with human behavior. The basic idea is to compare the map of attention -the saliency map -produced by the computational model with a fixation density map derived from eye movement experiments. This human attention map can be constructed as an integral of single impulses located at the positions of the successive fixation points. The resulting map has the same format as the computer-generated map, and can easily be compared by qualitative and quantitative methods. Some illustrative examples using a set of natural and synthetic color images show the potential of the validation method to assess the plausibility of the attention model.

show abstract

Section: Introductionmentioning

confidence: 99%

Empirical Validation of the Saliency-based Model of Visual Attention

Ouerhani¹,

Wartburg²,

Hügli³

et al. 2003

ELCVIA

120

View full text Add to dashboard Cite

show abstract

“…Visual attention has been applied in several robotic tasks, such as object recognition (Walther et al, 2004), object tracking (Frintrop & Kessel, 2009), simultaneous localization and mapping (SLAM) (Frintrop & Jensfelt, 2008) and exploration of unknown environment (Carbone et al, 2008). A few general visual perception models (Backer et al, 2001;Breazeal et al, 2001) are also presented by using visual attention. Furthermore, some research (Grossberg, 2005;2007) has proposed that the adaptive resonance theory (ART) (Carpenter & Grossberg, 2003) can predict the functional link between attention and processes of consciousness, learning, expectation, resonance and synchrony.…”

Section: Related Workmentioning

confidence: 99%

Development of an Autonomous Visual Perception System for Robots Using Object-Based Visual Attention

Yu¹,

Mann²,

Gosine³

2011

Recent Advances in Mobile Robotics

View full text Add to dashboard Cite

“…Typically, log-polar or foveated imaging techniques have been employed to simulate retinal sensing in the models of eye movements [28]. Recently, the saliency-based mapping approach has also been incorporated in some active vision models for eye movements [10], [1]. Nevertheless, modelling attentional shifts and gaze shifts based on their shared control circuits in a coherent system by their biologically-plausible relationship have not yet been found in any of these works.…”

Section: Introductionmentioning

confidence: 99%

“…In this way, human vision can use limited visual sources to effectively deal with complex visual selection tasks [21, p. 53, p. 80-88]. Visual (covert 1 ) attention has advantages of speediness, accuracy, and maintenance of mental processing and can freely undertake visual selection without eye movements, but may also need eye movements to extend the selection and improve performance in large-scale visual environments by a series of gaze shifts over time [9]. Because eye movements or fixation shifts take time and result in significantly different foveated images, the visual system must integrate these partially overlapping images in a spatio-temporal context for unified and coherent visual selection.…”

Section: Introductionmentioning

confidence: 99%

A computer vision model for visual-object-based attention and eye movements

Sun¹,

Fisher²,

Wang³

et al. 2008

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This paper presents a new computational framework for modelling visual-object based attention and attention-driven eye movements within an integrated system in a biologically inspired approach. Attention operates at multiple levels of visual selection by space, feature, object and group depending on the nature of targets and visual tasks. Attentional shifts and gaze shifts are constructed upon their common process circuits and control mechanisms but also separated from their different function roles, working together to fulfil flexible visual selection tasks in complicated visual environments. The framework integrates the important aspects of human visual attention and eye movements resulting in sophisticated performance in complicated natural scenes. The proposed approach aims at exploring a useful visual selection system for computer vision, especially for usage in cluttered natural visual environments.

show abstract

Data- and model-driven gaze control for an active-vision system

Cited by 94 publications

References 37 publications

Empirical Validation of the Saliency-based Model of Visual Attention

Empirical Validation of the Saliency-based Model of Visual Attention

Development of an Autonomous Visual Perception System for Robots Using Object-Based Visual Attention

A computer vision model for visual-object-based attention and eye movements

Contact Info

Product

Resources

About