A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation
Romanian Journal of Information Science and Technology · 30.06.2026 · 29 (2) · 115-127
DOI: 10.59277/romjist.2026.2.02 ↗Kurz gefasst
Fachartikel in der Zeitschrift Romanian Journal of Information Science and Technology, online erschienen am 05.06.2025. Verfasst von Vlad OLARU und 2 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben.
Abstract (Originalsprache)
This paper presents a framework that supports the implementation of parallel solutions for the parametric maximum flow computational models widely 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), which 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.
Zitieren
APA
OLARU, V., FLOREA, M., & SMINCHISESCU, C. (2026). A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation. Romanian Journal of Information Science and Technology, 29(2), 115-127. https://doi.org/10.59277/romjist.2026.2.02
Vancouver
OLARU V, FLOREA M, SMINCHISESCU C. A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation. Romanian Journal of Information Science and Technology. 2026;29(2):115-127. doi:10.59277/romjist.2026.2.02
BibTeX
@article{OLARU2026,
author = {OLARU, Vlad and FLOREA, Mihai and SMINCHISESCU, Cristian},
title = {A Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation},
journal = {Romanian Journal of Information Science and Technology},
year = {2026},
volume = {29},
number = {2},
pages = {115--127},
doi = {10.59277/romjist.2026.2.02}
}
EUVIMED