...
首页> 外文期刊>Mechanical systems and signal processing >Increasing the computational efficient of digital cross correlation by a vectorization method
【24h】

Increasing the computational efficient of digital cross correlation by a vectorization method

机译:通过矢量化方法提高数字互相关的计算效率

获取原文
获取原文并翻译 | 示例
           

摘要

This study presents a vectorization method for use in MATLAB programming aimed at increasing the computational efficiency of digital cross correlation in sound and images, resulting in a speedup of 6.387 and 36.044 times compared with performance values obtained from looped expression. This work bridges the gap between matrix operations and loop iteration, preserving flexibility and efficiency in program testing. This paper uses numerical simulation to verify the speedup of the proposed vectorization method as well as experiments to measure the quantitative transient displacement response subjected to dynamic impact loading. The experiment involved the use of a high speed camera as well as a fiber optic system to measure the transient displacement in a cantilever beam under impact from a steel ball. Experimental measurement data obtained from the two methods are in excellent agreement in both the time and frequency domain, with discrepancies of only 0.68%. Numerical and experiment results demonstrate the efficacy of the proposed vectorization method with regard to computational speed in signal processing and high precision in the correlation algorithm. We also present the source code with which to build MATLAB-executable functions on Windows as well as Linux platforms, and provide a series of examples to demonstrate the application of the proposed vectorization method.
机译:这项研究提出了一种用于MATLAB编程的矢量化方法,旨在提高声音和图像中数字互相关的计算效率,与从循环表达式获得的性能值相比,可加快6.387倍和36.044倍。这项工作弥合了矩阵运算和循环迭代之间的鸿沟,在程序测试中保留了灵活性和效率。本文使用数值模拟来验证所提出的矢量化方法的加速性,并通过实验来测量动态冲击载荷下的定量瞬态位移响应。实验涉及使用高速摄像机以及光纤系统来测量在钢球撞击下悬臂梁的瞬态位移。从这两种方法获得的实验测量数据在时域和频域上都非常一致,差异仅为0.68%。数值和实验结果证明了该矢量化方法在信号处理的计算速度和相关算法的高精度方面的有效性。我们还提供了用于在Windows和Linux平台上构建MATLAB可执行功能的源代码,并提供了一系列示例来演示所提出的矢量化方法的应用。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号