Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About

About

A. Augusto de Sousa finished his PhD in 1996 at the Faculty of Engineering, University of Porto (FEUP), Portugal, in the areas of Computer Graphics/Image Synthesis and Parallel Computing. He has been a lecturer and professor at the same Faculty since 1983, in areas related to Computer Graphics and Computer Architecture.


He was, between October 2014 and October 2022, a member of the executive board of FEUP, with the position of Vice-President of the Pedagogical Council. He was, from 2008 to 2014, director of the Integrated Master in Informatics and Computing Engineering at FEUP and, from 2000 to 2003, a member of the first Board that installed the Degree in Journalism and Communication Sciences at the University of Porto. He was a member of the Scientific Committee of ProDEI (Doctoral Program in Computer Engineering at FEUP) from its foundation in 2005 until May 2023. He is a member of the Department Council of the DEI (Computer Engineering Department of FEUP) and was several times elected member of the Pedagogic Council and the Scientific Council of FEUP.


He has been a researcher at INESC TEC since 1985, where he coordinates the Computer Graphics group of the HumanISE Unit and was coordinator of the Information Systems and Computer Graphics Unit between 1998 and 2000. He was the supervisor of two PhD theses, in Optimization of Visualization in Extensive 3D Scenes and in Storage, Processing and Visualization of Spatio-temporal Data, as well as co-supervisor of three PhD theses in Image Synthesis, Virtual Reality and Automatic Modeling of Virtual Urban Environments. He has supervised several MSc theses in several areas of Computer Graphics, Virtual Reality and Geographic Information Systems.


A. Augusto de Sousa has been involved in several R&D projects generically related to Advanced/Intuitive Interaction, Image Synthesis and Virtual Reality. He was the Principal Investigator of several FCT-funded projects in Spatial-Temporal Data Processing and Visualization, Expedient Modeling and Visualization of Urban Virtual Environments and Multisensorial Virtual Environments. He collaborated on a European project in the area of Advanced Interaction for 3D Modeling. He participated in the organisation and scientific committee of numerous national and international conferences and was the responsible organiser of three international conferences.


He was a member, in two different moments, of the direction of the EUROGRAPHICS Portuguese Chapter, having occupied the positions of President, Vice-President and Treasurer, as well as, inherently, member of the Executive Committee of the EUROGRAPHICS Association.

Interest
Topics
Details

Details

  • Name

    Augusto Sousa
  • Role

    Senior Researcher
  • Since

    01st March 1985
004
Publications

2024

Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2024, Volume 4: VISAPP, Rome, Italy, February 27-29, 2024

Authors
Radeva, P; Furnari, A; Bouatouch, K; de Sousa, AA;

Publication
VISIGRAPP (4): VISAPP

Abstract

2024

Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2024, Volume 3: VISAPP, Rome, Italy, February 27-29, 2024

Authors
Radeva, P; Furnari, A; Bouatouch, K; de Sousa, AA;

Publication
VISIGRAPP (3): VISAPP

Abstract

2024

Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2024, Volume 2: VISAPP, Rome, Italy, February 27-29, 2024

Authors
Radeva, P; Furnari, A; Bouatouch, K; de Sousa, AA;

Publication
VISIGRAPP (2): VISAPP

Abstract

2024

Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2024, Volume 1: GRAPP, HUCAPP and IVAPP, Rome, Italy, February 27-29, 2024

Authors
Rogers, TB; Méneveaux, D; Ziat, M; Ammi, M; Jänicke, S; Purchase, HC; Bouatouch, K; de Sousa, AA;

Publication
VISIGRAPP (1): GRAPP, HUCAPP, IVAPP

Abstract

2024

AIMSM - A Mechanism to Optimize Systems with Multiple AI Models: A Case Study in Computer Vision for Autonomous Mobile Robots

Authors
Ferreira, BG; de Sousa, AJM; Reis, LP; de Sousa, AA; Rodrigues, R; Rossetti, R;

Publication
Progress in Artificial Intelligence - 23rd EPIA Conference on Artificial Intelligence, EPIA 2024, Viana do Castelo, Portugal, September 3-6, 2024, Proceedings, Part III

Abstract
This article proposes the Artificial Intelligence Models Switching Mechanism (AIMSM), a novel approach to optimize system resource utilization by allowing systems to switch AI models during runtime in dynamic environments. Many real-world applications utilize multiple data sources and various AI models for different purposes. In many of those applications, every AI model doesn’t have to operate all the time. The AIMSM strategically allows the system to activate and deactivate these models, focusing on system resource optimization. The switching of each AI model can be based on any information, such as context or previous results. In the case study of an autonomous mobile robot performing computer vision tasks, the AIMSM helps the system to achieve a significant increment in performance, with a 50% average increase in frames per second (FPS) rate, for this specific case study, assuming that no erroneous switching occurred. Experimental results have demonstrated that the AIMSM can improve system resource utilization efficiency when properly implemented, optimize overall resource consumption, and enhance system performance. The AIMSM presented itself as a better alternative to permanently loading all the models simultaneously, improving the adaptability and functionality of the systems. It is expected that using the AIMSM will yield a performance improvement that is particularly relevant to systems with multiple AI models of a complex nature, where such models do not need to be all continuously executed or systems that will benefit from lower resource usage. Code is available at https://github.com/BrunoGeorgevich/AIMSM. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Supervised
thesis

2023

Accessibility Guidelines Proposal for the Interaction Design of Mobile Applications: Creating a More Inclusive User Experienc

Author
Mariana Oliveira Ramos

Institution
UP-FEUP

2023

Enhancing Research Data Lifecycle: Solving Observation-centric and Reproducibility Challenges

Author
Artur Jorge da Silva Rocha

Institution
UP-FEUP

2022

Enhancing Research Data Lifecycle: Solving Observation-centric and Reproducibility Challenges

Author
Artur Jorge da Silva Rocha

Institution
UP-FEUP

2022

Augmented Reality in Industrial Equipment

Author
João Pedro Pinheiro de Lacerda Campos

Institution
UP-FEUP

2021

cooperative and distributed location-based decision support

Author
Artur Jorge da Silva Rocha

Institution
UP-FEUP