TurboPixels: Fast Superpixels Using Geometric Flows

Authors:
Alex Levinshtein;Adrian Stere;Kiriakos N. Kutulakos;David J. Fleet;Sven J. Dickinson;Kaleem Siddiqi
Affiliations:
University of Toronto, Toronto;University of Toronto, Toronto;University of Toronto, Toronto;University of Toronto, Toronto;University of Toronto, Toronto;McGill University, Montreal
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2009

Citing 0
Cited 41

Towards artistic minimal rendering

NPAR '10 Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering
Resampling structure from motion

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Semantic segmentation of urban scenes using dense depth maps

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Superpixels and supervoxels in an energy optimization framework

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Supervised label transfer for semantic segmentation of street scenes

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Turbopixel segmentation using Eigen-images

IEEE Transactions on Image Processing
Efficient algorithms for image and high dimensional data processing using eikonal equation on graphs

ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part II
A hypergraph reduction algorithm for joint segmentation and classification of satellite image content

CIARP'10 Proceedings of the 15th Iberoamerican congress conference on Progress in pattern recognition, image analysis, computer vision, and applications
Spatiotemporal closure

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Multichannel segmentation using contour relaxation: fast super-pixels and temporal propagation

SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Discriminative segmentation of microscopic cellular images

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Evolving content-driven superpixels for accurate image representation

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
Content based image retrieval using bag-of-regions

MMM'12 Proceedings of the 18th international conference on Advances in Multimedia Modeling
Micro perceptual human computation for visual tasks

ACM Transactions on Graphics (TOG)
Towards automatic polyp detection with a polyp appearance model

Pattern Recognition
Fast high dynamic range image deghosting for arbitrary scene motion

Proceedings of Graphics Interface 2012
Dynamic range compression by differential zone mapping based on psychophysical experiments

Proceedings of the ACM Symposium on Applied Perception
Optimal Image and Video Closure by Superpixel Grouping

International Journal of Computer Vision
Perceptual grouping using superpixels

MCPR'12 Proceedings of the 4th Mexican conference on Pattern Recognition
Combining boundary and region features inside the combinatorial pyramid for topology-preserving perceptual image segmentation

Pattern Recognition Letters
Image colorization using similar images

Proceedings of the 20th ACM international conference on Multimedia
Multispectral piecewise planar stereo using Manhattan-world assumption

Pattern Recognition Letters
Online semantic mapping of urban environments

SC'12 Proceedings of the 2012 international conference on Spatial Cognition VIII
Streaming hierarchical video segmentation

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
SEEDS: superpixels extracted via energy-driven sampling

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Road scene segmentation from a single image

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Semantic road segmentation via multi-scale ensembles of learned features

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Graphics Interaction: High dynamic range image deghosting by fast approximate background modelling

Computers and Graphics
Partition cortical surfaces into supervertices: method and application

MeshMed'12 Proceedings of the 2012 international conference on Mesh Processing in Medical Image Analysis
Multifeature analysis and semantic context learning for image classification

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Efficient pixel-grouping based on dempster's theory of evidence for image segmentation

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
A linear programming based method for joint object region matching and labeling

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Multitarget tracking of pedestrians in video sequences based on particle filters

Advances in Multimedia
Artistic minimal rendering with lines and blocks

Graphical Models
Special Section on Expressive Graphics: Pixelated image abstraction with integrated user constraints

Computers and Graphics
Robust human body segmentation based on part appearance and spatial constraint

Neurocomputing
Unsupervised Natural Image Segmentation via Bayesian Ying-Yang Harmony Learning Theory

Neurocomputing
Visual tracking using superpixel-based appearance model

ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Superpixel-wise semi-supervised structural sparse coding classifier for image segmentation

Engineering Applications of Artificial Intelligence
User assisted disparity remapping for stereo images

Image Communication
Efficient semantic image segmentation with multi-class ranking prior

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.16

Visualization

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.