Abstract

We describe a geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels. It produces segments that, on one hand, respect local image boundaries, while, on the other hand, limiting undersegmentation through a compactness constraint. It is very fast, with complexity that is approximately linear in image size, and can be applied to megapixel sized images with high superpixel densities in a matter of minutes. We show qualitative demonstrations of high-quality results on several complex images. The Berkeley database is used to quantitatively compare its performance to a number of oversegmentation algorithms, showing that it yields less undersegmentation than algorithms that lack a compactness constraint while offering a significant speedup over N-cuts, which does enforce compactness.

Keywords

Compact spaceConstraint (computer-aided design)Image (mathematics)LimitingSpeedupArtificial intelligenceComputer scienceComputer visionAlgorithmPattern recognition (psychology)MathematicsGeometry

Affiliated Institutions

Related Publications

Publication Info

Year
2009
Type
article
Volume
31
Issue
12
Pages
2290-2297
Citations
1130
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1130
OpenAlex

Cite This

Alex Levinshtein, A. Stere, Kiriakos N. Kutulakos et al. (2009). TurboPixels: Fast Superpixels Using Geometric Flows. IEEE Transactions on Pattern Analysis and Machine Intelligence , 31 (12) , 2290-2297. https://doi.org/10.1109/tpami.2009.96

Identifiers

DOI
10.1109/tpami.2009.96