A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Data- and Model-Driven Gaze Control for an Active-Vision System
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object-based visual attention for computer vision
Artificial Intelligence
Evaluation of Visual Attention Models for Robots
ICVS '06 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems
A Coherent Computational Approach to Model Bottom-Up Visual Attention
IEEE Transactions on Pattern Analysis and Machine Intelligence
Implementation of visual attention system using bottom-up saliency map model
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
An attentional approach for perceptual grouping of spatially distributed patterns
Proceedings of the 29th DAGM conference on Pattern recognition
Is bottom-up attention useful for object recognition?
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Goal-directed search with a top-down modulated computational attention system
PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition
A Novel Hierarchical Framework for Object-Based Visual Attention
Attention in Cognitive Systems
Towards Standardization of Evaluation Metrics and Methods for Visual Attention Models
Attention in Cognitive Systems
Testing landmark identification theories in virtual environments
SC'10 Proceedings of the 7th international conference on Spatial cognition
Visual attention mechanism for a social robot
Applied Bionics and Biomechanics - Personal Care Robotics
| Hi-index | 0.00 |
This paper proposes a novel approach to construct saliency map of color contrast and an enhanced technique for inhibition of return on this map for artificial visual attention. The ability to handle dynamic scenes is also included in the model by introducing a memory based mechanism. For the process of color map construction the traditionally followed concept of double-opponent colors is extended by implementing the concepts of contrast from the subject of color theory. In context of inhibition of return, the color based inhibition is also modeled according to recent research in human vision apart from the commonly implemented spatial inhibition. The proposed methods have produced results compatible with the existing models of visual attention whereas the region-based nature of the proposed technique renders advantages of precise localization of the foci of attention, proper representation of the shapes of the attended objects, and accelerated computation time.