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

• Type: Article in International Scientific Journal
• Date: 2023

Authors

Magalhaes, SC (Author) Other; Filipe Neves Santos (Author) FEUP; Machado, P (Author) Other; António Paulo Moreira (Author) FEUP; Dias, J (Author) Other

Journal

Title: Engineering Applications of Artificial Intelligence

Vol. 117

ISSN: 0952-1976

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 7 Citations

Scopus - 14 Citations

Other information

Authenticus ID: P-00X-FW1

DOI: 10.1016/j.engappai.2022.105604

Abstract (EN): 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 %.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15