Implementation of Scale Invariant Feature Transform detector on FPGA for low-power wearable devices for prostheses control,International Journal of Circuit Theory and Applications

当前位置： X-MOL 学术 › Int. J. Circ. Theory Appl. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Implementation of Scale Invariant Feature Transform detector on FPGA for low-power wearable devices for prostheses control
International Journal of Circuit Theory and Applications ( IF 1.8 ) Pub Date : 2021-05-02 , DOI: 10.1002/cta.3025
Attila Fejér _{1,

2} , Zoltán Nagy ₂ , Jenny Benois‐Pineau ₁ , Péter Szolgay ₂ , Aymar Rugy ₃ , Jean‐Philippe Domenger ₁

Affiliation

In this paper we describe an FPGA implementation of the Scale Invariant Feature Transform (SIFT) algorithm. The FPGA is required as its a lightweight device which makes it ideal for vision-guided hybrid neuro-prostheses utilised for upper limbs replacement. SIFT point detection is needed for computation of coordinates of the object-to-grasp in a wearable multi-camera system. A modified SIFT algorithm is proposed and an implementation of it into C/C++ language on Xilinx ZCU102 FPGA board. The proposed hybrid hardware/software solution is compared to other hardware or hybrid implementations of the SIFT algorithm and with the baseline software detector OpenSIFT. The algorithm optimised for FPGA gives an average precision of 0.84 and the average recall of 0.94 in SIFT-point detection compared to the baseline.

中文翻译：

用于假肢控制的低功耗可穿戴设备的 FPGA 尺度不变特征变换检测器的实现

在本文中，我们描述了尺度不变特征变换 (SIFT) 算法的 FPGA 实现。需要 FPGA 作为轻量级设备，使其成为用于上肢置换的视觉引导混合神经假肢的理想选择。需要 SIFT 点检测来计算可穿戴多相机系统中物体到抓取的坐标。提出了一种改进的SIFT算法，并在Xilinx ZCU102 FPGA板上用C/C++语言实现。将提议的混合硬件/软件解决方案与 SIFT 算法的其他硬件或混合实现以及基线软件检测器 OpenSIFT 进行比较。与基线相比，针对 FPGA 优化的算法在 SIFT 点检测中的平均精度为 0.84，平均召回率为 0.94。

更新日期：2021-07-05

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文本刊介绍/投稿指南11