Performance characterization on embedded systems for Edge AI person-detection models

 

Na minha lista:
Detalhes bibliográficos
Autores: Cabrera-Quiros, Laura, Orozco-Retana, Kimberly
Formato: artículo original
Estado:Versión publicada
Data de Publicação:2025
Descrição:This paper presents a hardware performance characterization for two Edge AI platforms: Raspberry Pi 4 and NVIDIA Jetson Nano, for the task of automatic people detection using a deep learning model. For comparison purposes, we use the MLPerf Inference Benchmark evaluation system. The characterization considers the results from an SSD-Mobilenet object-detection model using two different datasets, one with 80 different object classes and another with only people. Comparison metrics consider model accuracy, latency, queries processed per second, and samples processed per second under the evaluation of different execution scenarios.
País:Portal de Revistas TEC
Recursos:Instituto Tecnológico de Costa Rica
Repositorio:Portal de Revistas TEC
Idioma:Español
OAI Identifier:oai:ojs.pkp.sfu.ca:article/7754
Acesso em linha:https://revistas.tec.ac.cr/index.php/tec_marcha/article/view/7754
Palavra-chave:EdgeIA
NVIDIA Jetson Nano
Raspberry Pi 4
MLPerf
Inference Benchmark
SSD-MobileNet
Edge AI
MLPerf Inference Benchmark