Name
Abstract | ||
|---|---|---|
Unsupervised over-segmentation of an image into super-pixels is a common preprocessing step for image parsing algorithms. Superpixels are used as both regions of support for feature vectors and as a starting point for the final segmentation. In this paper we investigate incorporating a priori information into superpixel segmentations. We learn a probabilistic model that describes the spatial density of the object boundaries in the image. We then describe an over-segmentation algorithm that partitions this density roughly equally between superpixels whilst still attempting to capture local object boundaries. We demonstrate this approach using road scenes where objects in the center of the image tend to be more distant and smaller than those at the edge. We show that our algorithm successfully learns this foveated spatial distribution and can exploit this knowledge to improve the segmentation. Lastly, we introduce a new metric for evaluating vision labeling problems. We measure performance on a challenging real-world dataset and illustrate the limitations of conventional evaluation metrics. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICCV.2009.5459246 | Kyoto |
Keywords | Field | DocType |
computer vision,image segmentation,probability,vectors,evaluation metrics,feature vectors,image parsing algorithm,probabilistic model,road scenes,scene shape priors,spatial distribution,superpixel segmentation,unsupervised over-segmentation,vision labeling problem | Computer vision,Feature vector,Pattern recognition,Segmentation,Computer science,A priori and a posteriori,Image segmentation,Preprocessor,Artificial intelligence,Pixel,Statistical model,Prior probability | Conference |
Volume | Issue | ISSN |
2009 | 1 | 1550-5499 E-ISBN : 978-1-4244-4419-9 |
ISBN | Citations | PageRank |
978-1-4244-4419-9 | 10 | 0.52 |
References | Authors | |
15 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alastair P. Moore | 1 | 59 | 4.07 |
| Simon Prince | 2 | 914 | 60.61 |
| Jonathan Warrell | 3 | 494 | 18.95 |
| Umar Mohammed | 4 | 179 | 10.30 |
| Graham Jones | 5 | 28 | 1.57 |