A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation

This paper presents a framework that supports the implementation of parallel solutions for the widespread parametric maximum flow computational routines used in image segmentation algorithms. The framework is based on supergraphs, a special construction combining several image graphs into a larger one, and works on various architectures (multi-core or GPU), either locally or remotely in a cluster of computing nodes. The framework can also be used for performance evaluation of parallel implementations of maximum flow algorithms. We present the case study of a state-of-the-art image segmentation algorithm based on graph cuts, Constrained Parametric Min-Cut (CPMC), that uses the parallel framework to solve parametric maximum flow problems, based on a GPU implementation of the well-known push-relabel algorithm. Our results indicate that real-time implementations based on the proposed techniques are possible.

[1]  Alexander Sorkine-Hornung,et al.  Cache-efficient graph cuts on structured grids , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Andrew V. Goldberg,et al.  Experimental Evaluation of a Parametric Flow Algorithm , 2006 .

[3]  Jacques Carlier,et al.  Handbook of Scheduling - Algorithms, Models, and Performance Analysis , 2004 .

[4]  Andrew V. Goldberg,et al.  A new approach to the maximum flow problem , 1986, STOC '86.

[5]  Mohamed E. Hussein,et al.  On Implementing Graph Cuts on CUDA , 2007 .

[6]  Vladimir Kolmogorov,et al.  Applications of parametric maxflow in computer vision , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Jian Sun,et al.  Parallel graph-cuts by adaptive bottom-up merging , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  P. J. Narayanan,et al.  CUDA cuts: Fast graph cuts on the GPU , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Eric V. Denardo,et al.  Flows in Networks , 2011 .

[10]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Robert E. Tarjan,et al.  A Fast Parametric Maximum Flow Algorithm and Applications , 1989, SIAM J. Comput..

[12]  M. R. Rao,et al.  Combinatorial Optimization , 1992, NATO ASI Series.

[13]  Joseph Y.-T. Leung,et al.  Handbook of Scheduling: Algorithms, Models, and Performance Analysis , 2004 .

[14]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[15]  Cristian Sminchisescu,et al.  Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Olga Veksler,et al.  Graph Cuts in Vision and Graphics: Theories and Applications , 2006, Handbook of Mathematical Models in Computer Vision.

[17]  Cristian Sminchisescu,et al.  Constrained parametric min-cuts for automatic object segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Xue-Cheng Tai,et al.  A study on continuous max-flow and min-cut approaches , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Dorit S. Hochbaum,et al.  The Pseudoflow Algorithm: A New Algorithm for the Maximum-Flow Problem , 2008, Oper. Res..

[20]  Ronen Basri,et al.  Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.