next up previous
Next: The Focus of Attention Up: Bottom-up saliency Previous: Feature Computations

Fusing Saliencies

All feature maps of one feature are combined into a conspicuity map yielding one map for each feature: $ I = \sum_i {\cal W}(I'_i)$, $ O = \sum_\theta {\cal W}(O'_\theta)$, $ C = \sum_\gamma {\cal W}(C'_\gamma)$. The bottom-up saliency map $ S_{bu}$ is finally determined by fusing the conspicuity maps: $ S_{bu} = {\cal W}(I) + {\cal W}(O) + {\cal W}(C)$

The exclusivity weighting $ {\cal W}$ is a very important strategy since it enables the increase of the impact of relevant maps. Otherwise, a region peaking out in a single feature would be lost in the bulk of maps and no pop-out would be possible. In our context, important maps are those that have few highly salient peaks. For weighting maps according to the number of peaks, each map $ M$ is divided by the square root of the number of local maxima $ m$ that exceed a threshold $ t$: $ {\cal W}(M) = M / \sqrt{m} \quad \forall m: m > t. $ Furthermore, the maps are normalized after summation relative to the largest value within the summed maps. This yields advantages over the normalization relative to a fixed value (details in [7]).

root 2005-01-27