UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Scene Shape Priors for Superpixel Segmentation

Moore, AP; Prince, SJD; Warrell, J; Mohammed, U; Jones, G; (2009) Scene Shape Priors for Superpixel Segmentation. In: 2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV). (pp. 771 - 778). IEEE

Full text not available from this repository.


Unsupervised over-segmentation of an image into superpixels 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.

Type: Proceedings paper
Title: Scene Shape Priors for Superpixel Segmentation
Event: 12th IEEE International Conference on Computer Vision
Location: Kyoto, JAPAN
Dates: 2009-09-29 - 2009-10-02
ISBN-13: 978-1-4244-4419-9
URI: http://discovery.ucl.ac.uk/id/eprint/174843
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item