Abstract
In this paper we develop a new method for high- lighting visually salient regions of an image based upon a known visual search task. The proposed method uses a robust model of instantaneous visual attention (i.e. "bottom- up") combined with a pixel probability map derived from the automatic detection of a previously-seen object (task-dependent i.e. "top-down") . The objects to be recognised are parameterised quickly in advance by a viewpoint-invariant spatial distribution of SURF interest- points. The bottom-up and top-down object probability images are fused to produce a task-dependent saliency map. We validate our method using observer eye-tracker data collected under object search-and-count tasking. Our method shows 10% higher overlap with true attention areas under task compared to bottom- up saliency alone. The new combined saliency map is further used to develop a new intelligent compression technique which is an extension of DCT encoding. We demonstrate our technique on surveillance-style footage throughout.
Original language | English |
---|---|
Title of host publication | ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings |
Pages | 480-485 |
Number of pages | 6 |
ISBN (Electronic) | 9781424455621 |
DOIs | |
Publication status | Published - 2009 |
Event | 2009 IEEE International Conference on Signal and Image Processing Applications - Kuala Lumpur, Malaysia Duration: 18 Nov 2009 → 19 Nov 2009 |
Conference
Conference | 2009 IEEE International Conference on Signal and Image Processing Applications |
---|---|
Abbreviated title | ICSIPA09 |
Country/Territory | Malaysia |
City | Kuala Lumpur |
Period | 18/11/09 → 19/11/09 |