• Corpus ID: 18629224

Dynamical optical flow of saliency maps for predicting visual attention

@article{Patrone2016DynamicalOF,
  title={Dynamical optical flow of saliency maps for predicting visual attention},
  author={Aniello Raffaele Patrone and Christian Valuch and Ulrich Ansorge and Otmar Scherzer},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.07324}
}
Saliency maps are used to understand human attention and visual fixation. However, while very well established for static images, there is no general agreement on how to compute a saliency map of dynamic scenes. In this paper we propose a mathematically rigorous approach to this prob- lem, including static saliency maps of each video frame for the calculation of the optical flow. Taking into account static saliency maps for calculating the optical flow allows for overcoming the aperture problem… 

Figures and Tables from this paper

Saliency Sandbox - Bottom-up Saliency Framework
TLDR
The Saliency Sandbox is introduced, a framework for the fast implementation and prototyping of saliency maps, which employs a flexible architecture that allows designing newSaliency maps by combining existing and new approaches such as Itti & Koch, GBVS, Boolean Maps and many more.

References

SHOWING 1-10 OF 60 REFERENCES
A Benchmark of Computational Models of Saliency to Predict Human Fixations
TLDR
A benchmark data set containing 300 natural images with eye tracking data from 39 observers is proposed to compare model performances and it is shown that human performance increases with the number of humans to a limit.
Spatio-temporal saliency model to predict eye movements in video free viewing
TLDR
This paper presents a spatio-temporal saliency model that predicts eye movements and compares the salient areas of each frame predicted by these saliency maps to the eye positions of different subjects during a video free viewing experiment with a large database.
Regularized Feature Reconstruction for Spatio-Temporal Saliency Detection
TLDR
A new spatio-temporal saliency detection framework on the basis of regularized feature reconstruction is proposed, which achieves the best performance over several state-of-the-art approaches.
Computational modelling of visual attention
TLDR
Five important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment, providing a framework for a computational and neurobiological understanding of visual attention.
A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression
TLDR
Extensive tests of videos, natural images, and psychological patterns show that the proposed PQFT model is more effective in saliency detection and can predict eye fixations better than other state-of-the-art models in previous literature.
Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention
  • R. Peters, L. Itti
  • Psychology, Biology
    2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
TLDR
This study demonstrates the advantages of integrating BU factors derived from a saliency map and TD factors learned from image and task contexts in predicting where humans look while performing complex visually-guided behavior.
Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics
TLDR
This paper compares the ranking of 12 state-of-the art saliency models using 12 similarity metrics and shows that some of the metrics are strongly correlated leading to a redundancy in the performance metrics reported in the available benchmarks.
Video saliency incorporating spatiotemporal cues and uncertainty weighting
TLDR
Experimental results show that the proposed method significantly outperforms state-of-the-art video saliency detection models.
GAFFE: A Gaze-Attentive Fixation Finding Engine
TLDR
A new algorithm is presented that selects image regions as likely candidates for fixation, and these regions are shown to correlate well with fixations recorded from human observers.
SUNDAy: Saliency Using Natural Statistics for Dynamic Analysis of Scenes
TLDR
This work generalizes the saliency framework to dynamic scenes and develops a simple, efficient, and online bottom-up saliency algorithm that matches the performance of more complex state of the art algorithms in predicting human fixa- tions during free-viewing of videos.
...
...