Modal Control Of An Attentive Vision System

Clark, James J.; Ferrier, Nicola

doi:10.1109/ccv.1988.590032

Cited by 136 publications

(73 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After all, the system needs to know which image region is the one to be regarded as foreground for any figureground segmentation to be initiated. Psychophysical studies on visual attention [40,41] have long served as inspiration for computational models [42,43], out of which many have been used in robotics for applications such as gaze control [44]. Despite differences in features used and level of biological relevance, these models all generate image points or regions that are conspicuous with respect to its surroundings, so as to direct computational resources towards regions that are more likely to be of importance to the overall system.…”

Section: Initialization and Interactionmentioning

confidence: 99%

Detecting, segmenting and tracking unknown objects using multi-label MRF inference

Björkman

Bergström

Kragić

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

This article presents a unified framework for detecting, segmenting and tracking unknown objects in everyday scenes, allowing for inspection of object hypotheses during interaction over time. A heterogeneous scene representation is proposed, with background regions modeled as a combinations of planar surfaces and uniform clutter, and foreground objects as 3D ellipsoids. Recent energy minimization methods based on loopy belief propagation, tree-reweighted message passing and graph cuts are studied for the purpose of multi-object segmentation and benchmarked in terms of segmentation quality, as well as computational speed and how easily methods can be adapted for parallel processing. One conclusion is that the choice of energy minimization method is less important than the way scenes are modeled. Proximities are more valuable for segmentation than similarity in colors, while the benefit of 3D information is limited. It is also shown through practical experiments that, with implementations on GPUs, multiobject segmentation and tracking using state-of-art MRF inference methods is feasible, despite the computational costs typically associated with such methods.

show abstract

Section: Initialization and Interactionmentioning

confidence: 99%

Detecting, segmenting and tracking unknown objects using multi-label MRF inference

Björkman

Bergström

Kragić

2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…The saliency map encodes the ability of an area to attract one's gaze. Since the first models (Clark & Ferrier, 1988;Tsotsos et al, 1995;Itti et al, 1998), their performance has increased significantly, as shown by the on-line MIT benchmark (Bylinskii et al, 2015). However, several studies have pointed out that, 20 in many contexts, top-down factors clearly take the precedence over bottomup factors to explain gaze behavior (Tatler et al, 2011;Einhäuser et al, 2008;Nyström & Holmqvist, 2008).…”

Section: Introductionmentioning

confidence: 99%

Introducing context-dependent and spatially-variant viewing biases in saccadic models

Meur

Coutrot

2016

Vision Research

View full text Add to dashboard Cite

Previous research showed the existence of systematic tendencies in viewing behavior during scene exploration. For instance, saccades are known to follow a positively skewed, long-tailed distribution, and to be more frequently initiated in the horizontal or vertical directions. In this study, we hypothesize that these viewing biases are not universal, but are modulated by the semantic visual category of the stimulus. We show that the joint distribution of saccade amplitudes and orientations significantly varies from one visual category to another. These joint distributions are in addition spatially variant within the scene frame. We demonstrate that a saliency model based on this better understanding of viewing behavioral biases and blind to any visual information outperforms well-established saliency models. We also propose a saccadic model that takes into account classical low-level features and spatially-variant and context-dependent viewing biases. This model outperforms state-of-the-art saliency models, and provides scanpaths in close agreement with human behavior. The better description of viewing biases will not only improve current models of visual attention but could also influence many other applications such as the design of human-computer interfaces, patient diagnosis or image/video processing applications.

show abstract

“…The background modelling technique described here is not restricted to curves; it could also be applied to real-time trackers based on polygons or other geometrical representations [23,14,17]. Some tracking applications, surveillance for instance, call for a panoramic field of view which can be achieved by a pan-tilt head [8,22,21,6]. Such a head is used in the experiments reported here.…”

Section: Introductionmentioning

confidence: 99%