77 documents found, page 1 of 8
Hardware-assisted range image generation for LiDAR point clouds
Oliveira, Fábio; Ferreira, Vitor; Pinto, Sandro; Gomes, Tiago Manuel RibeiroAs the need for efficient 3D data processing increases, particularly in autonomous driving applications, fast and resource-efficient methods for structuring and representing LiDAR data, such as range images (RIs), have become crucial. This letter presents a hardware-accelerated algorithm for generating RIs from 3D LiDAR point clouds, tailored for embedded platforms featuring Field-Programmable Gate Arrays (FPGA...
Decentor: the rise of intelligent edge devices
Costa, Diogo Emanuel Carvalho; Costa, Miguel Ângelo Peixoto; Monteiro, João L.; Gomes, Tiago Manuel Ribeiro; Pinto, SandroThe increasing concerns regarding data privacy have triggered a paradigm shift in machine learning (ML) systems, moving the inference and part of the training process from the cloud, which continues to perform model updates, to the deep edge. This new approach, known as Federated Learning (FL), reduces the workloads on the remote servers and network infrastructure, while enhancing overall data privacy. Recent r...
MSBN-SPose: A Multi-Scale Bayesian Neuro-Symbolic approach for sitting posture ...
Tavares, Adriano; Carlos Lima; Lima, Carlos; Gomes, Tiago Manuel Ribeiro; Liang, YanchunPosture recognition is critical in modern educational and office environments for preventing musculoskeletal disorders and maintaining cognitive performance. Existing methods based on human keypoint detection typically rely on convolutional neural networks (CNNs) and single-scale features, which limit representation capacity and suffer from overfitting under small-sample conditions. To address these issues, we ...
IA&AI: Interference analysis in multi-core embedded AI systems
Oliveira, Afonso; Moreira, Gonçalo; Costa, Diogo Emanuel Carvalho; Pinto, Sandro; Gomes, Tiago Manuel RibeiroSignificant advances in Artificial Intelligence (AI) over the past decade have opened new aisles of exploration for industries such as automotive and industrial robotics, leading to the widespread adoption of AI. To meet the demands of modern applications, embedded platforms have evolved into highly heterogeneous designs, transitioning from simple microcontroller-based systems to intricate platforms with multip...
ALFA: advanced LiDAR framework for automotive applications
Roriz, Ricardo João Rei; Cunha, Luís; Campos, André; Gomes, Tiago Manuel RibeiroThe automotive industry is rapidly moving towards the deployment of fully autonomous vehicles, which rely on advanced driver-assistance systems (ADAS) and robust perception systems for safe and efficient navigation. Among these technologies, Light Detection and Ranging (LiDAR) sensors have gained prominence for their ability to provide high-resolution 3D representations of the vehicle’s surroundings in real-tim...
TREE: bridging the gap between reconfigurable computing and secure execution
Pereira, Sérgio Augusto Gomes; Gomes, Tiago Manuel Ribeiro; Cabral, Jorge; Pinto, SandroTrusted Execution Environments (TEEs) have become a pivotal technology for securing a wide spectrum of security-sensitive applications. With modern com puting systems shifting to heterogeneous architectures, integrating TEE support into these systems is paramount. One promising line of research has proposed leveraging FPGA technology to provide promising TEE solutions. Despite their potential, current implement...
SecureQNN: Shielding the intellectual property of QNNs in TinyML systems
Costa, Miguel; Gomes, Tiago Manuel Ribeiro; Pinto, SandroBuilding accurate Machine Learning (ML) models requires substantial expertise and large-scale datasets typically only available in big data companies. These companies have been selling their models as Machine Learning as a Service. However, concerns about data privacy and the appliance of ML in mission-critical scenarios are forcing ML computation to move from the cloud to the deep edge, near sensor data. If ed...
RAOCSL: a BERT-based strategy for identifying learner confusion under class imb...
Zhao, Tongyu; Gao, Jiaying; Feng, Yu; Zu, Yatong; Tavares, Adriano; Gomes, Tiago Manuel Ribeiro; Pinto, Sandro; Xu, HaoUnderstanding and identifying the nature of learner confusion is important for online learning platforms. In this study, we address this problem by analyzing forum posts from large-scale online courses. However, due to the large volume of comments and frequent interactions, confusion posts are often overlooked. Existing methods and models, while capable of detecting confusion, typically rely on linguistic featu...
FOG: Fast Octree Generator for LiDAR point clouds
Roriz, Ricardo; Costa, Diogo Emanuel Carvalho; Ekpanyapong, Mongkol; Gomes, Tiago Manuel RibeiroAs the need for realistic and immersive 3-D representations of the environment continues to increase across various industries, finding efficient ways to represent data has become paramount. A well-known approach to partitioning 3-D space into a structured data format is the use of octrees, primarily due to their efficiency in handling both sparse and dense 3-D data. This method is particularly useful in applic...
FOG-Zip: Bitstream Compression for Octree-Encoded LiDAR Data
Roriz, Ricardo João Rei; Cabral, Jorge; Pinto, Sandro; Gomes, Tiago Manuel RibeiroLight detection and ranging (LiDAR) sensors play a critical role in enabling precise and reliable environmental perception for autonomous vehicles. However, handling the large amounts of data they generate presents a significant challenge. With the emergence of standards, such as the geometry based point cloud compression (G-PCC) standard, octrees have been used as a key data structure for compressing 3-D light...