Abstract | ||
---|---|---|
We present a non-parametric unsupervised colour image segmentation system that is fast and retains significant perceptual correspondence with the input data. The method uses a region merging approach based on statistics of growing local structures. A two-stage algorithm is employed during which neighbouring regions of homogeneity are traced using feature gradients between groups of pixels, thus giving priority to topological relations. The system finds spatially cohesive and globally salient image regions usually without losing smaller localised areas of high saliency. Unoptimised implementations of the method work nearly in real-time, handling multiple frames a second. The system is successfully applied to problems such as object detection and tracking. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/WIAMIS.2009.5031464 | WIAMIS |
Keywords | Field | DocType |
globally salient image regions,multistage region merging,image segmentation,nonparametric unsupervised colour image segmentation system,object tracking,gradient methods,feature gradients,object detection,generic colour image segmentation,image colour analysis,merging,pixel,real time,kernel | Kernel (linear algebra),Computer vision,Object detection,Pattern recognition,Salience (neuroscience),Segmentation,Computer science,Image segmentation,Video tracking,Artificial intelligence,Pixel,Salient | Conference |
ISBN | Citations | PageRank |
978-1-4244-3610-1 | 0 | 0.34 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gaurav Gupta | 1 | 14 | 7.06 |
Alexandra Psarrou | 2 | 199 | 27.14 |
Anastassia Angelopoulou | 3 | 102 | 21.29 |