Sciweavers

Share
ICASSP
2011
IEEE

A visual attention model combining top-down and bottom-up mechanisms for salient object detection

9 years 3 months ago
A visual attention model combining top-down and bottom-up mechanisms for salient object detection
Selective attention in the human visual system is performed as the way that humans focus on the most important parts when observing a visual scene. Many bottom-up computational models of visual attention have been devised to get the saliency map for an image, which are data-driven or task-independent. However, studies show that the taskdriven or top-down mechanism also plays an important role during the formation of visual attention, especially with the cases of object detection and location. In this paper, we proposed a new computational visual attention model by combining bottom-up and top-down mechanisms for manmade object detection in scenes. This model shows that the statistical characteristics of orientation features can be used as top-down clues to help for determining the location for salient objects in natural scenes. Experiments confirm the effectiveness of this visual attention model.
Yuming Fang, Weisi Lin, Chiew Tong Lau, Bu-Sung Le
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Yuming Fang, Weisi Lin, Chiew Tong Lau, Bu-Sung Lee
Comments (0)
books