Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
About

About

I got a Ph.D. in Electrical and Computers Engineering, at Universidade of Porto, in 1994.

I am currently Associate Professor at the Electrical and Computers Engineering Department, Engineering Faculty of the University of Porto (FEUP), where I teach in the areas of communication systems and signal processing.

I am a Researcher at INESC TEC since 1985 and my research interests include image and video processing and computer vision.

Interest
Topics
Details

Details

001
Publications

2018

BMOG: boosted Gaussian Mixture Model with controlled complexity for background subtraction

Authors
Martins, I; Carvalho, P; Corte Real, L; Alba Castro, JL;

Publication
Pattern Analysis and Applications

Abstract

2017

BMOG: Boosted Gaussian Mixture Model with Controlled Complexity

Authors
Martins, I; Carvalho, P; Corte Real, L; Luis Alba Castro, JL;

Publication
Pattern Recognition and Image Analysis - Lecture Notes in Computer Science

Abstract

2016

Bio-inspired Boosting for Moving Objects Segmentation

Authors
Martins, I; Carvalho, P; Corte Real, L; Luis Alba Castro, JL;

Publication
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2016)

Abstract
Developing robust and universal methods for unsupervised segmentation of moving objects in video sequences has proved to be a hard and challenging task. State-of-the-art methods show good performance in a wide range of situations, but systematically fail when facing more challenging scenarios. Lately, a number of image processing modules inspired in biological models of the human visual system have been explored in different areas of application. This paper proposes a bio-inspired boosting method to address the problem of unsupervised segmentation of moving objects in video that shows the ability to overcome some of the limitations of widely used state-of-the-art methods. An exhaustive set of experiments was conducted and a detailed analysis of the results, using different metrics, revealed that this boosting is more significant when challenging scenarios are faced and state-of-the-art methods tend to fail.

2016

Video Based Group Tracking and Management

Authors
Pereira, A; Familiar, A; Moreira, B; Terroso, T; Carvalho, P; Corte Real, L;

Publication
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2016)

Abstract
Tracking objects in video is a very challenging research topic, particularly when people in groups are tracked, with partial and full occlusions and group dynamics being common difficulties. Hence, its necessary to deal with group tracking, formation and separation, while assuring the overall consistency of the individuals. This paper proposes enhancements to a group management and tracking algorithm that receives information of the persons in the scene, detects the existing groups and keeps track of the persons that belong to it. Since input information for group management algorithms is typically provided by a tracking algorithm and it is affected by noise, mechanisms for handling such noisy input tracking information were also successfully included. Performed experiments demonstrated that the described algorithm outperformed state-of-the-art approaches.

2013

Multi-view codec with low-complexity encoding for Distributed Video Coding

Authors
Ciobanu, L; Corte Real, L;

Publication
MULTIMEDIA TOOLS AND APPLICATIONS

Abstract
The low-complexity encoding, as fundamental requirement of Distributed Video Coding, relies on performing the bulk of computation at decoder, including tasks as the generation of side information and particularly, inter-camera registration in the case of multi-view systems with complete-overlapped views and free motion of the cameras (e.g., video surveillance). In Ciobanu and Corte-Real (Multimedia Tools Appl 48(3):411-436, 2010) we introduced a codec-independent solution for such tasks at decoder. In this paper, we present a multi-view Wyner-Ziv codec (IWZ) designed for the architecture and scenarios from Ciobanu and Corte-Real (2010) (e.g., free motion of the cameras, no a priori knowledge of the instant camera positions, no feedback channel), based on transform domain (DCT), block-based coset coding. We aimed to achieve a compromise between the low encoder complexity and the rate-distortion performance. A detailed evaluation is presented for comparison with conventional coding (Intra 4x4 and Intra 16x16). Practical results show a better overall performance of the proposed codec at low bitrates.

Supervised
thesis

2017

Image Processing for Event Detection in Retail Environments

Author
Pedro Daniel Nunes Querido

Institution
UP-FEUP

2016

Multicamera System for Automatic Positioning of Objects in Game Sports

Author
Miguel Soares Moreira

Institution
UP-FEUP

2016

Segmentation of Moving Objects

Author
Maria Isabel de Castro Lopes Martins Pinto Ferreira

Institution
Outra

2015

Human Motion Analysis in Video Sequences for Telerehabilitation Systems

Author
Ana Clara Ferreira Matos

Institution
UP-FEUP

2015

Seguimento de Grupos de Pessoas Utilizando Vídeo

Author
Alexandra Maria Pereira Familiar

Institution
UP-FEUP