A parallel PDE-based numerical algorithm for computing the Optical Flow in hybrid systems

被引:8
|
作者
Cuomo, Salvatore [1 ]
De Michele, Pasquale [1 ]
Galletti, Ardelio [2 ]
Marcellino, Livia [2 ]
机构
[1] Univ Naples Federico II, Dept Math & Applicat, Str Vicinale Cupa Cintia 21, I-80126 Naples, Italy
[2] Univ Naples Parthenope, Dept Sci & Technol, Ctr Direz Isola C3, I-80143 Naples, Italy
关键词
Optical Flow; Partial differential equations; High performance computing; Graphic processor units; Hybrid architectures;
D O I
10.1016/j.jocs.2017.03.011
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
In this paper, we propose a fine-to-coarse parallelization strategy in order to exploit, in a case study, a parallel hybrid architecture. We consider the Optical Flow numerical problem, modelled by partial differential equations, and implement a parallel multilevel software. Our hybrid software solution is a smart combination between codes on Graphic Processor Units (GPUs) and standard scientific parallel computing libraries on a cluster. Numerical experiments, on real satellite image sequences coming from a large dataset in a big data scenario, together with application profiling, highlight good results in terms of performance for the proposed approach. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:228 / 236
页数:9
相关论文
共 50 条
  • [1] A PDE-based method for optical flow estimation
    Lu, Zongqing
    Xie, Weixin
    Pei, Jihong
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2006, : 78 - +
  • [2] Nonlinear Evolutionary PDE-Based Refinement of Optical Flow
    Doshi H.
    Kiran N.U.
    Machine Graphics and Vision, 2021, 30 (1-4): : 45 - 65
  • [3] A Dynamic Controller for PDE-Based Systems
    Pablo Flores-Flores, Juan
    Martinez Guerra, Rafael
    2019 IEEE 7TH INTERNATIONAL CONFERENCE ON CONTROL, MECHATRONICS AND AUTOMATION (ICCMA 2019), 2019, : 68 - 72
  • [4] Secure Consensus Control for PDE-Based Multiagent Systems Resist Hybrid Attacks
    Song, Xiaona
    Sun, Xiangliang
    Song, Shuai
    Zhang, Yijun
    IEEE SYSTEMS JOURNAL, 2023, 17 (02): : 3047 - 3058
  • [5] A python']python module for PDE-based numerical modelling
    Gross, Lutz
    Cumming, Ben
    Steube, Ken
    Weatherley, Dion
    APPLIED PARALLEL COMPUTING: STATE OF THE ART IN SCIENTIFIC COMPUTING, 2007, 4699 : 270 - +
  • [6] Toward a multi-level parallel framework on GPU cluster with PetSC-CUDA for PDE-based Optical Flow computation
    Cuomo, S.
    Galletti, A.
    Giunta, G.
    Marcellino, L.
    INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE, ICCS 2015 COMPUTATIONAL SCIENCE AT THE GATES OF NATURE, 2015, 51 : 170 - 179
  • [7] Parallel PDE-based simulations using the common component architecture
    Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL, United States
    不详
    不详
    不详
    不详
    不详
    不详
    不详
    不详
    Lect. Notes Comput. Sci. Eng., 2006, (327-381):
  • [8] Formal methods to generate parallel iterative codes for PDE-based applications
    Tang, PY
    ICECCS 2005: 10TH IEEE INTERNATIONAL CONFERENCE ON ENGINEERING OF COMPLEX COMPUTER SYSTEMS, PROCEEDINGS, 2005, : 106 - 115
  • [9] Fault detection using PDE-based observer in transport flow
    Idellette, Hermine Som Judith
    Cocquempot, Vincent
    Aitouche, Abdel
    ISA TRANSACTIONS, 2023, 142 : 112 - 122
  • [10] A PDE-Based Data Reconciliation Approach for Systems with Variations of Parameters
    Duangsri, Siwaporn
    Kheawhom, Soorathep
    Bumroongsri, Pornchai
    ENGINEERING JOURNAL-THAILAND, 2019, 23 (04): : 157 - 169