A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this paper, a new method of automatic focusing attention for a stereo pairs of image sequence is proposed. The proposed method is new in that it utilizes motion and depth information for the purpose of detecting FOA (focus of attention). Typical feature integration model is expanded to incorporate motion and depth stimulus in our suggested model. Suggested model is able to respond to motion stimulus by employing motion fields map as one of temporal features to the feature integration model, and also the disparity map obtained from a stereo pair of images is exploited as one of spatial visual features to form a set of topographic feature maps in our approach. The analysis of motion field map and incorporation of the result are distinct from some of the previous studies on spatial feature integration. We have tested our model with various kinds of real images such as stereo pairs of image sequences which have all kind of features (color, intensity, orientation, form, depth, motion), or the images which have just have only intensity, or have no depth or no motion information.