Benchmark analysis of yolo performance on edge intelligence devices

H Feng, G Mu, S Zhong, P Zhang, T Yuan - Cryptography, 2022 - mdpi.com
In the 5G intelligent edge scenario, more and more accelerator-based single-board
computers (SBCs) with low power consumption and high performance are being used as …

Programming for high-performance computing on edge accelerators

P Kang - Mathematics, 2023 - mdpi.com
The field of edge computing has grown considerably over the past few years, with
applications in artificial intelligence and big data processing, particularly due to its powerful …

Deep-learning blurring correction of images obtained from NIR single-pixel imaging

C Osorio Quero, D Durini… - Journal of the Optical …, 2023 - opg.optica.org
In challenging scenarios characterized by low-photon conditions or the presence of
scattering effects caused by rain, fog, or smoke, conventional silicon-based cameras face …

Optimized deep learning object recognition for drones using embedded gpu

PA Rad, D Hofmann, SAP Mendez… - 2021 26th IEEE …, 2021 - ieeexplore.ieee.org
Nowadays, drones can be seen in various applications in industry like surveillance and
transportation. Industrial drones leverage fully-fledged computer vision techniques, such as …

GPU-aided edge computing for processing the k nearest-neighbor query on SSD-resident data

P Velentzas, M Vassilakopoulos, A Corral - Internet of Things, 2021 - Elsevier
Edge computing aims at improving performance by storing and processing data closer to
their source. The k Nearest-Neighbor (k-NN) query is a common spatial query in several …

[PDF][PDF] Data and stream parallelism optimizations on GPUs

GA Araujo - 2022 - repositorio.pucrs.br
Nos dias de hoje, a maioria dos computadores são equipados com unidades de
processamento gráfico (GPUs) para prover capacidade massiva de paralelismo a baixo …

Enhancing 3D human pose estimation with NIR single-pixel imaging and time-of-flight technology: a deep learning approach

C Osorio Quero, D Durini… - Journal of the Optical …, 2024 - opg.optica.org
The extraction of 3D human pose and body shape details from a single monocular image is
a significant challenge in computer vision. Traditional methods use RGB images, but these …

Balancing Energy Efficiency and Portability: Assessing Domain-Specific Languages in Edge Platforms

Y Faqir-Rhazoui, L Costero… - 2024 20th International …, 2024 - ieeexplore.ieee.org
Edge computing stands as a crucial component of the IoT revolution. IoT benefits
significantly from reduced latency, enhancing real-time applications, and time-sensitive …

Машинное обучение в физике конденсированного состояния

КА Теников, АС Кочкин - Краевые задачи и математическое …, 2023 - elibrary.ru
МАШИННОЕ ОБУЧЕНИЕ В ФИЗИКЕ КОНДЕНСИРОВАННОГО СОСТОЯНИЯ КОРЗИНА
ПОИСК НАВИГАТОР ЖУРНАЛЫ КНИГИ ПАТЕНТЫ ПОИСК АВТОРЫ ОРГАНИЗАЦИИ …

A Survey on GPU-Based Visual Trackers

I Mohamed, I Elhenawy, A Salah - Recent Advances in Computer Vision …, 2023 - Springer
The object tracking problem is a key one in computer vision, and it is critical in a variety of
applications such as guided missiles, unmanned aerial vehicles, and video surveillance …