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

 

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Συγγραφείς: Cabrera-Quiros, Laura, Orozco-Retana, Kimberly
Μορφή: artículo original
Κατάσταση:Versión publicada
Ημερομηνία έκδοσης:2025
Περιγραφή: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.
Χώρα:Portal de Revistas TEC
Ίδρυμα:Instituto Tecnológico de Costa Rica
Repositorio:Portal de Revistas TEC
Γλώσσα:Español
OAI Identifier:oai:ojs.pkp.sfu.ca:article/7754
Διαθέσιμο Online:https://revistas.tec.ac.cr/index.php/tec_marcha/article/view/7754
Λέξη-Κλειδί :EdgeIA
NVIDIA Jetson Nano
Raspberry Pi 4
MLPerf
Inference Benchmark
SSD-MobileNet
Edge AI
MLPerf Inference Benchmark