A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Photomosaics
ACM SIGGRAPH 2006 Papers
Global contrast based salient region detection
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Hi-index | 0.00 |
This paper presents a method to display two types of images simultaneously in one image. One is for viewers at a far distance, and the other is for viewers closer to the screen. The basic idea is to overlay small images in high resolution (i.e. near-images) on a larger image in low resolution (i.e. far-image) by adjusting transparency of the near images. However, this simple overlay approach fails to provide acceptable visibility for both images. We propose to use a saliency map to emphasize important features of each image. By using this saliency map, it is possible to provide better visibility for both images, which this paper will illustrate with various examples.