Rui Policarpo Duarte

Dr. Rui Policarpo Duarte

Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento, Lisbon, Lisboa, Portugal
orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HCHelena Cruz
Helena Cruz
Mário VéstiasMário Véstias
Mário Véstias
JMJose Monteiro
Jose Monteiro
HNHorácio Neto
Horácio Neto
Rui Policarpo DuarteRui Policarpo Duarte
Rui Policarpo Duarte
Designing synthetic-aperture radar image formation systems can be challenging due to the numerous options of algorithms and devices that can be used. There are many SAR image formation algorithms, such as backprojection, matched-filter, polar format, Range–Doppler and chirp scaling algorithms. Each algorithm presents its own advantages and disadvantages considering efficiency and image quality; thus, we aim to introduce some of the most common SAR image formation algorithms and compare them based on these two aspects. Depending on the requisites of each individual system and implementation, there are many device options to choose from, for instance, FPGAs, GPUs, CPUs, many-core CPUs, and microcontrollers. We present a review of the state of the art of SAR imaging systems implementations. We also compare such implementations in terms of power consumption, execution time, and image quality for the different algorithms used.

19 May 2021 in IEEE Access
Verified
Journal Article
Open access
DPDaniel Pestana
Daniel Pestana
PMPedro R. Miranda
Pedro R. Miranda
JLJoão D. Lopes
João D. Lopes
Rui Policarpo DuarteRui Policarpo Duarte
Rui Policarpo Duarte
Mário VéstiasMário Véstias
Mário Véstias
JSJose de Sousa
Jose de Sousa
Object detection and classification is an essential task of computer vision. A very efficient algorithm for detection and classification is YOLO (You Look Only Once). We consider hardware architectures to run YOLO in real-time on embedded platforms. Designing a new dedicated accelerator for each new version of YOLO is not feasible given the fast delivery of new versions. This work's primary goal is to design a configurable and scalable core for creating specific object detection and classification systems based on YOLO, targeting embedded platforms. The core accelerates the execution of all the algorithm steps, including pre-processing, model inference and post-processing. It considers a fixed-point format, linearised activation functions, batch-normalisation, folding, and a hardware structure that exploits most of the available parallelism in CNN processing. The proposed core is configured for real-time execution of YOLOv3-Tiny and YOLOv4-Tiny, integrated into a RISC-V-based system-on-chip architecture and prototyped in an UltraScale XCKU040 FPGA (Field Programmable Gate Array). The solution achieves a performance of 32 and 31 frames per second for YOLOv3-Tiny and YOLOv4-Tiny, respectively, with a 16-bit fixed-point format. Compared to previous proposals, it improves the frame rate at a higher performance efficiency. The performance, area efficiency and configurability of the proposed core enable the fast development of real-time YOLO-based object detectors on embedded systems.

18 May 2020 in Algorithms
Verified
Journal Article
Open access
PDF file
Mário VéstiasMário Véstias
Mário Véstias
Rui Policarpo DuarteRui Policarpo Duarte
Rui Policarpo Duarte
JSJose de Sousa
Jose de Sousa
HNHorácio C. Neto
Horácio C. Neto
Deep learning is now present in a wide range of services and applications, replacing and complementing other machine learning algorithms. Performing training and inference of deep neural networks using the cloud computing model is not viable for applications where low latency is required. Furthermore, the rapid proliferation of the Internet of Things will generate a large volume of data to be processed, which will soon overload the capacity of cloud servers. One solution is to process the data at the edge devices themselves, in order to alleviate cloud server workloads and improve latency. However, edge devices are less powerful than cloud servers, and many are subject to energy constraints. Hence, new resource and energy-oriented deep learning models are required, as well as new computing platforms. This paper reviews the main research directions for edge computing deep learning algorithms.

25 November 2019 in IEEE Access
Verified
Journal Article
Open access
JVJoao Vieira
Joao Vieira
Rui Policarpo DuarteRui Policarpo Duarte
Rui Policarpo Duarte
HNHoracio C. Neto
Horacio C. Neto
This paper presents kNN STreaming Unit For Fpgas (kNN-STUFF), a modular, scalable and efficient Hardware/Software implementation of k-Nearest Neighbors (kNN) classifier targeting System on Chip (SoC) devices. It takes advantage of custom accelerators, implemented on the reconfigurable fabric of the SoC device, to perform most of the classifier’s workload, whereas the processor coordinates the accelerators and runs the remaining workload of the kNN algorithm. kNN-STUFF offers a highly flexible framework, where the designer has the possibility to define the number of parallel instances of the classifier and the parallelism within each instance. This capability allows creating the most suitable implementation for a target device of any size. Results show that kNN-STUFF, with 24 accelerators, attains performance improvements up to 67.4×, when compared to an optimized (-O3) software-only implementation of the kNN running on a single core of the ARM Cortex-A9 CPU. Furthermore, its energy efficiency improvements are as high as 50.6×.

27 July 2020 in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
Verified
Journal Article
Open access
MTMaxime THIEBAUT
Maxime THIEBAUT
JFJean-François Filipot
Jean-François Filipot
CMChristophe Maisondieu
Christophe Maisondieu
GDGuillaume Damblans
Guillaume Damblans
Rui Policarpo DuarteRui Policarpo Duarte
Rui Policarpo Duarte
Sylvain S. GuillouSylvain S. Guillou
Sylvain S. Guillou
Two coupled four-beam acoustic Doppler current profilers were used to provide simultaneous and independent measurements of the turbulent kinetic energy (TKE) dissipation rate ε and the TKE production rate P over a 36 h long period at a highly energetic tidal energy site in the Alderney Race. The eight-beam arrangement enabled the evaluation of the six components of the Reynolds stress tensor which allows for an improved estimation of the TKE production rate. Depth-time series of ε, P and the Reynolds stresses are provided. The comparison between ε and P was performed by calculating individual ratios of ε corresponding to P . The depth-averaged ratio ε / P averaged over whole flood and ebb tide were found to be 2.2 and 2.8 respectively, indicating that TKE dissipation exceeds TKE production. It is shown that the term of diffusive transport of TKE is significant. As a result, non-local transport is important to the TKE budget and the common assumption of a local balance, i.e. a balance between production and dissipation, is not valid at the measurement site. This article is part of the theme issue ‘New insights on tidal dynamics and tidal energy harvesting in the Alderney Race’.

29 August 2015
Verified
Book Chapter
Closed access
PDF file
André Ribeiro LourençoAndré Ribeiro Lourenço
André Ribeiro Lourenço
AAAna Priscila Alves
Ana Priscila Alves
CCCarlos Carreiras
Carlos Carreiras
Rui Policarpo DuarteRui Policarpo Duarte
Rui Policarpo Duarte
AFAna L. N. Fred
Ana L. N. Fred