TurboPixels: Fast Superpixels Using Geometric Flows

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.

[1]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[3]  Ronen Basri,et al.  Fast multiscale image segmentation , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[5]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[8]  Jitendra Malik,et al.  Recovering human body configurations: combining segmentation and recognition , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[9]  Jitendra Malik,et al.  Learning a classification model for segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[10]  Alexei A. Efros,et al.  Automatic photo pop-up , 2005, ACM Trans. Graph..

[11]  Jeffrey Mark Siskind,et al.  Image Segmentation with Ratio Cut - Supplemental Material , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Benjamin B. Kimia,et al.  Image segmentation by reaction-diffusion bubbles , 1995, Proceedings of IEEE International Conference on Computer Vision.

[13]  Jianbo Shi,et al.  Multiclass spectral clustering , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[14]  Richard S. Zemel,et al.  Learning and Incorporating Top-Down Cues in Image Segmentation , 2006, ECCV.

[15]  Kaleem Siddiqi,et al.  Hamilton-Jacobi Skeletons , 2002, International Journal of Computer Vision.

[16]  Jeffrey Mark Siskind,et al.  Image Segmentation with Ratio Cut , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Jianbo Shi,et al.  Spectral segmentation with multiscale graph decomposition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Ingemar J. Cox,et al.  "Ratio regions": a technique for image segmentation , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[19]  Sudeep Sarkar,et al.  Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Olivier D. Faugeras,et al.  Codimension-two geodesic active contours for the segmentation of tubular structures , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[21]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Anthony J. Yezzi,et al.  Gradient flows and geometric active contour models , 1995, Proceedings of IEEE International Conference on Computer Vision.

[23]  S. Zucker,et al.  Toward a computational theory of shape: an overview , 1990, eccv 1990.

[24]  Benjamin B. Kimia,et al.  Segmentation of Carpal Bones from 3d CT Images Using Skeletally Coupled Deformable Models , 1998, MICCAI.

[25]  Alexei A. Efros,et al.  Geometric context from a single image , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[26]  Kaleem Siddiqi,et al.  Area and length minimizing flows for shape segmentation , 1998, IEEE Trans. Image Process..

[27]  Richard M. Leahy,et al.  An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  V. Caselles,et al.  A geometric model for active contours in image processing , 1993 .

[30]  Ian H. Jermyn,et al.  Globally Optimal Regions and Boundaries as Minimum Ratio Weight Cycles , 2001, IEEE Trans. Pattern Anal. Mach. Intell..