Title | ||
---|---|---|
A visual attention model combining top-down and bottom-up mechanisms for salient object detection |
Abstract | ||
---|---|---|
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 task-driven 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 man-made 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. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5946648 | ICASSP |
Keywords | Field | DocType |
visual scene,salient object location determination,visual attention,human visual system,statistical orientation feature characteristics,statistical analysis,object detection,man-made object detection,top-down,bottom-up computational model,computational visual attention model,bottom-up,feature extraction,natural scenes,salient object detection,top-down mechanism,image saliency map,task-driven mechanism,computer model,bottom up,top down,visualization,indexing terms,selective attention,computational modeling,data mining | Visual search,Object detection,Computer vision,Pattern recognition,Human visual system model,Computer science,Visualization,Top-down and bottom-up design,Feature extraction,Computational model,Visual attention,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4577-0537-3 | 978-1-4577-0537-3 | 8 |
PageRank | References | Authors |
0.58 | 6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuming Fang | 1 | 1247 | 75.50 |
Weisi Lin | 2 | 5366 | 280.14 |
Chiew Tong Lau | 3 | 406 | 35.82 |
Bu-Sung Lee | 4 | 2119 | 140.18 |