Abstract

Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Ideally, every pixel within each superpixel region will belong to the same real-world object. Existing algorithms generate superpixels that forfeit many useful properties of the regular topology of the original pixels: for example, the nth superpixel has no consistent position or relationship with its neighbors. We propose a novel algorithm that produces superpixels that are forced to conform to a grid (a regular superpixel lattice). Despite this added topological constraint, our algorithm is comparable in terms of speed and accuracy to alternative segmentation approaches. To demonstrate this, we use evaluation metrics based on (i) image reconstruction (ii) comparison to human-segmented images and (iii) stability of segmentation over subsequent frames of video sequences.

Keywords

Artificial intelligencePixelComputer sciencePattern recognition (psychology)SegmentationImage segmentationPreprocessorParsingImage (mathematics)Computer vision

Affiliated Institutions

Related Publications

Guiding model search using segmentation

In this paper we show how segmentation as preprocessing paradigm can be used to improve the efficiency and accuracy of model search in an image. We operationalize this idea usin...

2005 298 citations

Publication Info

Year
2008
Type
article
Pages
1-8
Citations
372
Access
Closed

External Links

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

372
OpenAlex

Cite This

Alastair Moore, Simon J. D. Prince, Jonathan Warrell et al. (2008). Superpixel lattices. , 1-8. https://doi.org/10.1109/cvpr.2008.4587471

Identifiers

DOI
10.1109/cvpr.2008.4587471