arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.07815eess.IVcs.LGphysics.flu-dyn
收藏

基于机器学习策略的体积粒子图像测速粒子重建

Particle reconstruction of volumetric particle image velocimetry with strategy of machine learning

Zhejiang University(浙江大学);University of Michigan(密歇根大学);MicroVec. Inc.(MicroVec公司);Beihang University(北京航空航天大学)

Qi Gao, Shaowu Pan, Hongping Wang, Runjie Wei, Jinjun Wang

摘要:

有限二维投影下的三维粒子重构是一个欠定反问题,其精确解往往难以得到。通常,近似解可以通过迭代优化方法获得。在目前的工作中,提出了一种实用的粒子重建方法的基础上的卷积神经网络(CNN)与几何信息的功能。所提出的技术可以从任何传统的基于代数重建技术(ART)的方法产生的粒子分布的非常粗略的初始猜测细化粒子重建。与现有的基于ART的算法相比,新技术在重建质量、{对噪声的鲁棒性}方面有了显著的改善,并且在离线阶段至少快了一个数量级。

英文摘要:

Three-dimensional particle reconstruction with limited two-dimensional projections is an under-determined inverse problem that the exact solution is often difficult to be obtained. In general, approximate solutions can be obtained by iterative optimization methods. In the current work, a practical particle reconstruction method based on a convolutional neural network (CNN) with geometry-informed features is proposed. The proposed technique can refine the particle reconstruction from a very coarse initial guess of particle distribution generated by any traditional algebraic reconstruction technique (ART) based methods. Compared with available ART-based algorithms, the novel technique makes significant improvements in terms of reconstruction quality, {robustness to noises}, and at least an order of magnitude faster in the offline stage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑