Benchmarking edge computing devices for grape bunches and trunks detection using accelerated object detection single shot multibox deep learning models

Magalhães, S.C., Santos, F.N., Machado, P. ORCID: 0000-0003-1760-3871, Moreira, A.P. and Dias, J., 2023. Benchmarking edge computing devices for grape bunches and trunks detection using accelerated object detection single shot multibox deep learning models. Engineering Applications of Artificial Intelligence, 117 (Part A): 105604. ISSN 0952-1976

[img]
Preview
Text
1619042_Machado.pdf - Accepted version

Download (4MB) | Preview

Abstract

Purpose: Visual perception enables robots to perceive the environment. Visual data is processed using computer vision algorithms that are usually time-expensive and require powerful devices to process the visual data in real-time, which is unfeasible for open-field robots with limited energy. This work benchmarks the performance of different heterogeneous platforms for object detection in real-time. This research benchmarks three architectures: embedded GPU-Graphical Processing Units (such as NVIDIA Jetson Nano 2 GB and 4 GB, and NVIDIA Jetson TX2), TPU-Tensor Processing Unit (such as Coral Dev Board TPU), and DPU-Deep Learning Processor Unit (such as in AMD-Xilinx ZCU104 Development Board, and AMD-Xilinx Kria KV260 Starter Kit).

Methods: The authors used the RetinaNet ResNet-50 fine-tuned using the natural VineSet dataset. After the trained model was converted and compiled for target-specific hardware formats to improve the execution efficiency.

Conclusions and Results: The platforms were assessed in terms of performance of the evaluation metrics and efficiency (time of inference). Graphical Processing Units (GPUs) were the slowest devices, running at 3 FPS to 5 FPS, and Field Programmable Gate Arrays (FPGAs) were the fastest devices, running at 14 FPS to 25 FPS. The efficiency of the Tensor Processing Unit (TPU) is irrelevant and similar to NVIDIA Jetson TX2. TPU and GPU are the most power-efficient, consuming about 5 W. The performance differences, in the evaluation metrics, across devices are irrelevant and have an F1 of about 70 % and mean Average Precision (mAP) of about 60 %.

Item Type: Journal article
Publication Title: Engineering Applications of Artificial Intelligence
Creators: Magalhães, S.C., Santos, F.N., Machado, P., Moreira, A.P. and Dias, J.
Publisher: Elsevier
Date: January 2023
Volume: 117
Number: Part A
ISSN: 0952-1976
Identifiers:
NumberType
10.1016/j.engappai.2022.105604DOI
S0952197622005942Publisher Item Identifier
1619042Other
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 23 Nov 2022 13:51
Last Modified: 19 Nov 2023 03:00
URI: https://irep.ntu.ac.uk/id/eprint/47483

Actions (login required)

Edit View Edit View

Views

Views per month over past year

Downloads

Downloads per month over past year