Red grape detection with accelerated artificial neural networks in the FPGA's programmable logic

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Magalhães, Sandro Costa, Almeida, Marco, Santos, Filipe Neves dos, Moreira, António Paulo, Dias, Jorge
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909674714955776
author Magalhães, Sandro Costa
Almeida, Marco
Santos, Filipe Neves dos
Moreira, António Paulo
Dias, Jorge
author_facet Magalhães, Sandro Costa
Almeida, Marco
Santos, Filipe Neves dos
Moreira, António Paulo
Dias, Jorge
contents Robots usually slow down for canning to detect objects while moving. Additionally, the robot's camera is configured with a low framerate to track the velocity of the detection algorithms. This would be constrained while executing tasks and exploring, making robots increase the task execution time. AMD has developed the Vitis-AI framework to deploy detection algorithms into FPGAs. However, this tool does not fully use the FPGAs' PL. In this work, we use the FINN architecture to deploy three ANNs, MobileNet v1 with 4-bit quantisation, CNV with 2-bit quantisation, and CNV with 1-bit quantisation (BNN), inside an FPGA's PL. The models were trained on the RG2C dataset. This is a self-acquired dataset released in open access. MobileNet v1 performed better, reaching a success rate of 98 % and an inference speed of 6611 FPS. In this work, we proved that we can use FPGAs to speed up ANNs and make them suitable for attention mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02443
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Red grape detection with accelerated artificial neural networks in the FPGA's programmable logic
Magalhães, Sandro Costa
Almeida, Marco
Santos, Filipe Neves dos
Moreira, António Paulo
Dias, Jorge
Computer Vision and Pattern Recognition
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Machine Learning
Robotics
Robots usually slow down for canning to detect objects while moving. Additionally, the robot's camera is configured with a low framerate to track the velocity of the detection algorithms. This would be constrained while executing tasks and exploring, making robots increase the task execution time. AMD has developed the Vitis-AI framework to deploy detection algorithms into FPGAs. However, this tool does not fully use the FPGAs' PL. In this work, we use the FINN architecture to deploy three ANNs, MobileNet v1 with 4-bit quantisation, CNV with 2-bit quantisation, and CNV with 1-bit quantisation (BNN), inside an FPGA's PL. The models were trained on the RG2C dataset. This is a self-acquired dataset released in open access. MobileNet v1 performed better, reaching a success rate of 98 % and an inference speed of 6611 FPS. In this work, we proved that we can use FPGAs to speed up ANNs and make them suitable for attention mechanisms.
title Red grape detection with accelerated artificial neural networks in the FPGA's programmable logic
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Machine Learning
Robotics
url https://arxiv.org/abs/2507.02443