Color segmentation for visual attention of mobile robots

Aziz, Muhammad Zaheer; Shafik, M. Salah E.-N.; Mertsching, Bärbel; Munir, Asim

doi:10.1109/icet.2005.1558865

Cited by 4 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. nuq are created for each slice by applying a color segmentation procedure which groups similarly colored pixels to form regions (please refer to [21] or [22] for details regarding such segmentation methods which have been used in region-based attention). Additionally, a label map L that maps a position in the slice pn, mq to a region R i is generated.…”

Section: Motion Feature Magnitudesmentioning

confidence: 99%

Saliency-Guided Perceptual Grouping Using Motion Cues in Region-Based Artificial Visual Attention

Tünnermann¹,

Enns²,

Mertsching³

2013

Preprint

View full text Add to dashboard Cite

Region-based artificial attention constitutes a framework for bio-inspired attentional processes on an intermediate abstraction level for the use in computer vision and mobile robotics. Segmentation algorithms produce regions of coherently colored pixels. These serve as proto-objects on which the attentional processes determine image portions of relevance. A single region-which not necessarily represents a full object-constitutes the focus of attention. For many post-attentional tasks, however, such as identifying or tracking objects, single segments are not sufficient. Here, we present a saliency-guided approach that groups regions that potentially belong to the same object based on proximity and similarity of motion. We compare our results to object selection by thresholding saliency maps and a further attention-guided strategy.

show abstract

Section: Motion Feature Magnitudesmentioning

confidence: 99%

Saliency-Guided Perceptual Grouping Using Motion Cues in Region-Based Artificial Visual Attention

Tünnermann¹,

Enns²,

Mertsching³

2013

Preprint

View full text Add to dashboard Cite

show abstract

Region-Based Artificial Visual Attention in Space and Time

Tünnermann

Mertsching

2013

Cogn Comput

View full text Add to dashboard Cite

Affordance Estimation Enhances Artificial Visual Attention: Evidence from a Change-Blindness Study

et al. 2015

View full text Add to dashboard Cite

Artificial attention models have been proposed to simulate human attentional behavior for the purpose to predict such or to endow technical systems with the ability to filter relevant from irrelevant information in visual scenes. Such models are typically based on the concept of saliency, which reflects the conspicuity of a visual entity regarding features such as color, intensity or orientation. Besides these stimulus-driven processes, a lot of effort has been made to enhance the models with top-down influences, which are known to govern human attentional behavior. Mostly, this aspect is considered in the form of specific targets for visual search or very general characteristics as the gist of a scene. For human attention it has been shown that objects which afford actions-such as graspable items in the action space-attract attention. Here we show that an artificial attention model that estimates such affordances can better predict human performance in a change detection task than a classic bottom-up saliency model. The implications are twofold: (1) The results add further evidence that human attention is highly influenced by affordances, which we can objectively model and compare to an objective control based on visual saliency. (2) The integration of affordance estimation into technical attention systems provides a top-down influence which is not overly specific or general but guides attention to objects which are potential targets of actions and with respect to the physical capabilities of the system; this is an advancement for technical cognitive systems.

show abstract

Color segmentation for visual attention of mobile robots

Cited by 4 publications

References 22 publications

Saliency-Guided Perceptual Grouping Using Motion Cues in Region-Based Artificial Visual Attention

Saliency-Guided Perceptual Grouping Using Motion Cues in Region-Based Artificial Visual Attention

Region-Based Artificial Visual Attention in Space and Time

Affordance Estimation Enhances Artificial Visual Attention: Evidence from a Change-Blindness Study

Contact Info

Product

Resources

About