The detection of object regions based on local saliency has been with great interest in computer vision for its potential contributions to applications, such as recognition, because objects of interest could be contained in salient regions. However, regions are extracted from local salient locations by simple procedures without the global inference, resulting in poor segmentation of possible objects. In this paper, a two-strategy has been proposed to introduce local saliency into foreground subtraction, a color grouping method. By using only color information and no prior higher level knowledge about objects and scenes, multiple foreground regions are extracted simultaneously according to visual attention based salient locations. The prominence score is defined to further evaluate these regions for their possibility to contain objects of interest.
展开▼
