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

TL;DR

This paper demonstrates the deployment of accelerated artificial neural networks on FPGA's programmable logic for efficient red grape detection, achieving high accuracy and inference speed, thus enhancing robotic object detection capabilities.

Contribution

It introduces a novel FPGA deployment of quantized ANNs using the FINN architecture, improving detection speed and accuracy for robotic applications.

Findings

MobileNet v1 achieved 98% success rate

Inference speed reached 6611 FPS

FPGAs effectively accelerate ANNs for object detection

Abstract

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.