Abstract | ||
---|---|---|
We extend the classical notion of computational to multi-image data collected using a stationary pan-tilt-zoom (PTZ) camera by introducing the concept of : the requirement that the set of generated saliency maps should each assign the saliency value to unique regions of the environment that appear in more than one image. We show that processing each image independently will often fail to provide a consistent measure of saliency, and that using an image mosaic to quantify saliency suffers from several drawbacks. We then propose and an immediate extension, : a mosaic-free method for calculating a consistent measure of bottom-up saliency. Experimental results demonstrating the effectiveness of the proposed approach are presented. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s11263-015-0842-9 | International Journal of Computer Vision |
Keywords | Field | DocType |
Visual saliency,Pan-tilt-zoom camera | Computer vision,Kadir–Brady saliency detector,Salience (neuroscience),Computer science,Top-down and bottom-up design,Zoom,Artificial intelligence,Pan–tilt–zoom camera,Visual saliency | Journal |
Volume | Issue | ISSN |
116 | 2 | 0920-5691 |
Citations | PageRank | References |
0 | 0.34 | 28 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Garrett A. Warnell | 1 | 78 | 16.40 |
Philip David | 2 | 111 | 6.10 |
Chellappa, R. | 3 | 13050 | 1440.56 |