English

应用科学学报 ›› 2023, Vol. 41 ›› Issue (5): 831-839.doi: 10.3969/j.issn.0255-8297.2023.05.009

• 信号与信息处理 • 上一篇    

激光点云线性KNN算法FPGA实现及加速

陈小宇1, 阳梦雪1, 李常对1, 赵鹏程2   

  1. 1. 华中师范大学 物理科学与技术学院, 湖北 武汉 430079;
    2. 武汉大学 遥感信息工程学院, 湖北 武汉 430079
  • 收稿日期:2021-10-20 发布日期:2023-09-28
  • 通信作者: 陈小宇,博士,副教授,研究方向为嵌入式系统与应用、信号与信息处理。E-mail:chenxy@ccnu.edu.cn E-mail:chenxy@ccnu.edu.cn
  • 基金资助:
    国家自然科学基金（No.42101441）资助

Implementation and Acceleration of Linear KNN Algorithm for Laser Point Cloud Based on FPGA

CHEN Xiaoyu1, YANG Mengxue1, LI Changdui1, ZHAO Pengcheng2   

  1. 1. College of Physical Science and Technology, Central China Normal University, Wuhan 430079, Hubei, China;
    2. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, Hubei, China
  • Received:2021-10-20 Published:2023-09-28

PDF

199

摘要： 针对三维激光点云线性K最近邻（K-nearest neighbor,KNN）搜索耗时长的问题，提出了一种利用多处理器片上系统（multi-processor system on chip,MPSoC）现场可编程门阵列（field-programmable gate array，FPGA）实现三维激光点云KNN快速搜索的方法。首先给出了三维激光点云KNN算法的MPSoC FPGA实现框架；然后详细阐述了每个模块的设计思路及实现过程；最后利用MZU15A开发板和天眸16线旋转机械激光雷达搭建了测试平台，完成了三维激光点云KNN算法MPSoC FPGA加速的测试验证。实验结果表明：基于MPSoC FPGA实现的三维激光点云KNN算法能在保证邻近点搜索精度的情况下，减少邻近点搜索耗时。

关键词: 三维激光点云匹配, K最近邻算法, 现场可编程门阵列加速, 并行计算

Abstract: To address the time-consuming problem of 3D laser point cloud for linear K-nearest neighbor (KNN) search, a fast KNN search method based on multi-processor system on chip (MPSoC) field-programmable gate array (FPGA) is proposed. Firstly, the implementation framework of 3D laser point cloud KNN algorithm based on MPSoC FPGA is given. Then, the design ideas and implementation process of each module are elaborated. Finally, the proposed method is validated through tests and verification on platform built based on MZU15A development board and TM-LIDAR-16. Results demonstrate that the 3D laser point cloud KNN algorithm based on MPSoC FPGA can reduce time consumption while ensuring the accuracy of neighboring point search.

Key words: 3D laser point cloud matching, K-nearest neighbors (KNN) algorithm, fieldprogrammable gate array (FPGA) acceleration, parallel computing

中图分类号: