Abstract | ||
---|---|---|
By the guidance of attention, human visual system is able to locate objects of interest in complex scene. We propose a new visual saliency detection model for both image and video. Inspired by biological vision, saliency is defined locally. Lossy compression is adopted, where the saliency of a location is measured by the Incremental Coding Length(ICL). The ICL is computed by presenting the center patch as the sparsest linear representation of its surroundings. The final saliency map is generated by accumulating the coding length. The model is tested on both images and videos. The results indicate a reliable and robust saliency of our method. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICIP.2009.5414465 | Image Processing |
Keywords | Field | DocType |
lossy compression,image representation,coding length,sparsest linear representation,human visual system,biological vision,complex scene,saliency detection,incremental coding length,saliency map,sparse saliency detection,robust saliency,feature extraction,sparse coding,video coding,object detection,computer vision,incremental sparse saliency detection,center patch,new visual saliency detection,final saliency map,visualization,computational modeling,encoding,vectors,visual system | Computer vision,Object detection,Lossy compression,Kadir–Brady saliency detector,Pattern recognition,Visualization,Neural coding,Computer science,Salience (neuroscience),Human visual system model,Feature extraction,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-5655-0 | 978-1-4244-5655-0 | 13 |
PageRank | References | Authors |
0.63 | 6 | 5 |