A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation

TL;DR

This paper introduces a parallel framework leveraging supergraphs for efficient parametric maximum flow computations in image segmentation, enabling real-time processing on various hardware architectures.

Contribution

The paper proposes a novel parallel framework using supergraphs for parametric maximum flow problems, adaptable to multiple architectures, and demonstrates its application in real-time image segmentation.

Findings

Achieved real-time performance in image segmentation tasks.

Demonstrated the framework's effectiveness on GPU and multi-core systems.

Provided a case study with the CPMC algorithm using GPU-based push-relabel.

Abstract

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.