A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual interest and NPR: an evaluation and manifesto
Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering
Saliency-guided Enhancement for Volume Visualization
IEEE Transactions on Visualization and Computer Graphics
The Colour Image Processing Handbook (Optoelectronics, Imaging and Sensing)
The Colour Image Processing Handbook (Optoelectronics, Imaging and Sensing)
Real-time tracking of visually attended objects in interactive virtual environments
Proceedings of the 2007 ACM symposium on Virtual reality software and technology
Persuading Visual Attention through Geometry
IEEE Transactions on Visualization and Computer Graphics
ACM Transactions on Graphics (TOG)
Supporting order picking with Augmented Reality
ISMAR '08 Proceedings of the 7th IEEE/ACM International Symposium on Mixed and Augmented Reality
Salient region detection and segmentation
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Importance-driven compositing window management
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Directing attention and influencing memory with visual saliency modulation
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Display-adaptive window management for irregular surfaces
Proceedings of the ACM International Conference on Interactive Tabletops and Surfaces
| Hi-index | 0.00 |
We present a technique for dynamically directing a viewer's attention to a focus object by analyzing and modulating bottom-up salient features of a video feed. Rather than applying a static modulation strategy, we inspect the original image's saliency map, and modify the image automatically to favor the focus object. Image fragments are adaptively darkened, lightened and manipulated in hue according to local contrast information rather than global parameters. The goal is to suggest rather than force the attention of the user towards a specific location. The technique's goal is to apply only minimal changes to an image, while achieving a desired difference of saliency between focus and context regions of the image. Our technique exhibits temporal and spatial coherence and runs at interactive frame rates using GPU shaders. We present several application examples from the field of Mixed Reality, or more precisely Mediated Reality.