北京航空航天大学学报 ›› 2021, Vol. 47 ›› Issue (3): 486-499.doi: 10.13700/j.bh.1001-5965.2020.0452

• 论文 • 上一篇    下一篇

基于FPGA无人机影像快速低功耗高精度三维重建

李杰, 李一轩, 吴天生, 王昊榕, 梁敏   

  1. 山西财经大学 信息学院, 太原 030006
  • 收稿日期:2020-08-24 发布日期:2021-04-08
  • 通讯作者: 李杰 E-mail:lijiescu@aliyun.com
  • 作者简介:李杰,男,博士,副教授。主要研究方向:机器学习、计算机视觉和图像处理;李一轩,男,硕士研究生。主要研究方向:机器学习、计算机视觉和高能效计算;吴天生,男,硕士研究生。主要研究方向:机器视觉、数字图像处理和三维重建;王昊榕,女,硕士研究生。主要研究方向:机器视觉、数字图像处理和三维超分辨重建;梁敏,女,博士,副教授。主要研究方向:大数据技术和应用。
  • 基金资助:
    国家自然科学基金(61801279);山西省应用基础研究计划(201801D221160);山西省高等学校科技创新计划(STIP)(2019L0471);山西省研究生教育创新计划(2020SY175,2020SY176)

Fast, low-power and high-precision 3D reconstruction of UAV images based on FPGA

LI Jie, LI Yixuan, WU Tiansheng, WANG Haorong, LIANG Min   

  1. College of Information, Shanxi University of Finance and Economics, Taiyuan 030006, China
  • Received:2020-08-24 Published:2021-04-08
  • Supported by:
    National Natural Science Foundation of China (61801279); The Applied Basic Research Programs of Shanxi Province (201801D221160); Scientific and Technologial Innovation Programs of Higher Education Institutions in Shanxi (STIP)(2019L0471); Shanxi Graduate Education Innovation Project (2020SY175,2020SY176)[

摘要: 现有无人机(UAV)影像三维重建方法在功耗、时效等方面无法满足移动终端对低功耗、高时效的需求。为此,在有限资源FPGA平台下,结合指令优化策略和软硬件协同优化方法,提出一种基于FPGA高吞吐量硬件优化架构的无人机航拍影像快速低功耗高精度三维重建方法。首先,构建多尺度深度图融合算法架构,增强传统FPGA相位相关算法对不可信区域的鲁棒性,如低纹理、河流等区域。其次,结合高并行指令优化策略,提出高性能软硬件协同优化方案,实现多尺度深度图融合算法架构在有限资源FPGA平台的高效运行。最后,将现有CPU方法、GPU方法与FPGA方法进行综合实验比较,实验结果表明:FPGA方法在重建时间消耗上与GPU方法接近,比CPU方法快近20倍,但功耗仅为GPU方法的2.23%。

关键词: 低功耗, FPGA, 三维重建, 相位相关, 软硬件协同优化

Abstract: The existing 3D reconstruction methods based on Unmanned Aerial Vehicle (UAV) images cannot meet the mobile terminal's demand for low power consumption and high time efficiency. To tackle this issue, we propose a fast, low-power and high-precision 3D reconstruction method based on resource-constrained FPGA platforms, which combines instruction optimization strategy and hardware-software co-design method. First, we construct a multi-scale depth map fusion algorithm architecture to enhance the robustness of traditional FPGA phase correlation algorithms to untrustworthy areas, such as low-texture area and rivers. Secondly, based on the high parallel instruction optimization hardware acceleration function strategy, a high-performance hardware-software co-design scheme is proposed to realize the efficient operation of the multi-scale deep map fusion algorithm architecture on the FPGA platform with limited resources. Finally, we comprehensively compare the state-of-the-art CPU and GPU methods with our method. The experimental results show that our method is close to the GPU method in reconstruction time consumption, nearly 20 times faster than the CPU method, but the power consumption is only 2.23% of the GPU method.

Key words: low-power, FPGA, 3D reconstruction, phase correlation, hardware-software co-design

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发