Andrews Sobral

Andrews Sobral
ActiveEon · Machine Learning Team

Ph.D. on Computer Vision and Machine Learning

About

32
Publications
67,337
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,639
Citations
Additional affiliations
May 2017 - present
ActiveEon
Position
  • Researcher
Description
  • Senior AI Architect at ActiveEon, Paris - France. In short, my activities are: - Lead a team of PhDs on AI & Machine Learning; - Development of end-to-end AI workflows; - Development of parallel & distributed AI workflows; - Development of multi-node & multi-GPU AI workflows; - Development of a large-scale distributed AutoML workflow for hyperparameter optimization & neural architecture search;
June 2015 - August 2015
Autonomous University of Barcelona
Position
  • Doctoral research stage
September 2013 - May 2017
La Rochelle Université
Position
  • PhD Student
Description
  • Supported by a CAPES/Brazil scholarship. Focus on Robust Background Subtraction.
Education
September 2013 - May 2017
La Rochelle Université
Field of study
  • Computer Vision and Machine Learning
March 2010 - December 2012
Universidade Federal da Bahia
Field of study
  • Mechatronics Engineering
June 2004 - June 2009
Area1 - Engineering School
Field of study
  • Computer Engineering

Publications

Publications (32)
Article
Full-text available
Recent research on problem formulations based on decomposition into low-rank plus sparse matrices shows a suitable framework to separate moving objects from the background. The most representative problem formulation is the Robust Principal Component Analysis (RPCA) solved via Principal Component Pursuit (PCP) which decomposes a data matrix in a lo...
Chapter
Full-text available
The BGSLibrary has been designed to provides an easy-to-use C++ framework and tools to perform background subtraction. First released in March 2012, currently the library offers 32 background subtraction algorithms. The source code is available under GNU GPL v3 license and the library is free for non-commercial use, open source and platform indepen...
Chapter
Full-text available
The LRSLibrary provides a collection of low-rank and sparse decomposition algorithms in MATLAB. The library was designed for motion segmentation in videos, but it can be also used or adapted for other computer vision problems.
Preprint
Full-text available
Finding the best mathematical equation to deal with the different challenges found in complex scenarios requires a thorough understanding of the scenario and a trial and error process carried out by experts. In recent years, most state-of-the-art equation discovery methods have been widely applied in modeling and identification systems. However, eq...
Thesis
Full-text available
This thesis introduces the recent advances on decomposition into low-rank plus sparse matrices and tensors, as well as the main contributions to face the principal issues in moving object detection. First, we present an overview of the state-of-the-art methods for low-rank and sparse decomposition, as well as their application to background modelin...
Article
Full-text available
Human pose estimation refers to the estimation of the location of body parts and how they are connected in an image. Human pose estimation from monocular images has wide applications (e.g., image indexing). Several surveys on human pose estimation can be found in the literature, but they focus on a certain category; for example, model-based approac...
Presentation
Full-text available
Recent advances on low-rank and sparse decomposition for moving object detection Atelier: Enjeux dans la détection d’objets mobiles par soustraction de fond.
Presentation
Full-text available
Background subtraction is an important task for visual surveillance systems. However, this task becomes more complex when the data size grows since the real-world scenario requires larger data to be processed in a more efficient way, and in some cases, in a continuous manner. Until now, most of background subtraction algorithms were designed for mo...
Conference Paper
Full-text available
Background subtraction is an important task for visual surveillance systems. However, this task becomes more complex when the data size grows since the real-world scenario requires larger data to be processed in a more efficient way, and in some cases, in a continuous manner. Until now, most of background subtraction algorithms were designed for mo...
Conference Paper
Full-text available
Background model initialization is commonly the first step of the background subtraction process. In practice, several challenges appear and perturb this process such as dynamic background, bootstrapping, illumination changes, noise image, etc. In this context, this work aims to investigate the background model initialization as a matrix completion...
Presentation
Full-text available
Background model initialization is commonly the first step of the background subtraction process. In practice, several challenges appear and perturb this process such as dynamic background, bootstrapping, illumination changes, noise image, etc. In this context, this work aims to investigate the background model initialization as a matrix completion...
Conference Paper
Full-text available
Background model initialization is commonly the first step of the background subtraction process. In practice, several challenges appear and perturb this process such as dynamic background, bootstrapping, illumination changes, noise image, etc. In this context, this work aims to investigate the background model initialization as a matrix completion...
Conference Paper
Full-text available
The development of automated video-surveillance applications for maritime environment is a very difficult task due to the complexity of the scenes: moving water, waves, etc. The motion of the objects of interest (i.e. ships or boats) can be mixed with the dynamic behavior of the background (non-regular patterns). In this paper, a double-constrained...
Presentation
Full-text available
The development of automated video-surveillance applications for maritime environment is a very difficult task due to the complexity of the scenes: moving water, waves, etc. The motion of the objects of interest (i.e. ships or boats) can be mixed with the dynamic behavior of the background (non-regular patterns). In this paper, a double-constrained...
Book
Full-text available
Atualmente, sistemas de vídeo para monitoramento de tráfego urbano têm sido adotados com maior frequência. Através das imagens capturadas do trânsito, sistemas inteligentes baseados em visão computacional procuram extrair informações relevantes tais como a densidade, velocidade, localização e sentido dos veículos presentes na cena. Entretanto, as s...
Conference Paper
Full-text available
Background modeling and foreground object detection is the first step in visual surveillance system. The task becomes more difficult when the background scene contains significant variations, such as water surface, waving trees and sudden illumination conditions, etc. Recently, subspace learning model such as Robust Principal Component Analysis (RP...
Conference Paper
Full-text available
Accurate and efficient foreground detection is an important task in video surveillance system. The task becomes more critical when the background scene shows more variations, such as water surface, waving trees, varying illumination conditions, etc. Recently, Robust Principal Components Analysis (RPCA) shows a very nice framework for moving object...
Conference Paper
Full-text available
Background subtraction (BS) is the art of separating moving objects from their background. The Background Modeling (BM) is one of the main steps of the BS process. Several subspace learning (SL) algorithms based on matrix and tensor tools have been used to perform the BM of the scenes. However, several SL algorithms work on a batch process increasi...
Presentation
Full-text available
Background subtraction (BS) is the art of separating moving objects from their background. The Background Modeling (BM) is one of the main steps of the BS process. Several subspace learning (SL) algorithms based on matrix and tensor tools have been used to perform the BM of the scenes. However, several SL algorithms work on a batch process increasi...
Conference Paper
Full-text available
Background subtraction (BS) is the art of separating moving objects from their background. The Background Modeling (BM) is one of the main steps of the BS process. Several subspace learning (SL) algorithms based on matrix and tensor tools have been used to perform the BM of the scenes. However, several SL algorithms work on a batch process increasi...
Conference Paper
Full-text available
This work proposes a framework for facial expression recognition based on generalized procrustes analysis. The proposed system classifies seven different facial expressions: happiness, anger, sadness, surprise, disgust, fear and neutral. The proposed system was evaluated with the MUG Facial Expression database. Experimental results shows that the p...
Conference Paper
Full-text available
This work proposes an automatic human-face expression recognition system that classifies seven different facial expressions: happiness, anger, sadness, surprise, disgust, fear and neutral. The experimental results show that the proposed system achieves the best hit hate using a linear discriminant classifier, 99.71% and 99.55% for MUG and FEEDTUM d...
Presentation
Full-text available
Matrix and Tensor Tools for Computer Vision
Conference Paper
Full-text available
The BGSLibrary provides a free easy-to-use C++ open source framework to perform background subtraction (BGS). Currently the library provides 29 BGS algorithms. In this work the library is described and the benchmark and performance evaluation of all BGS algorithms are shown. It is expected that the results presented here can help to choice the most...
Presentation
Full-text available
This work proposes a holistic method for highway traffic video classification based on vehicle crowd properties. The method classifies the traffic congestion into three classes: light, medium and heavy. This is done by usage of average crowd density and crowd speed. Firstly, the crowd density is estimated by background subtraction and the crowd spe...
Conference Paper
Full-text available
This work proposes a holistic method for highway traffic video classification based on vehicle crowd properties. The method classifies the traffic congestion into three classes: light, medium and heavy. This is done by usage of average crowd density and crowd speed. Firstly, the crowd density is estimated by background subtraction and the crowd spe...
Conference Paper
Full-text available
A robótica é a ciência de perceber e manipular o ambiente real através de dispositivos mecânicos controlados por computador. Exemplos bem sucedidos de sistemas robóticos incluem plataformas móveis para a exploração planetária, braços robóticos nas linhas de montagem de indústrias, extração de petróleo em águas profundas, entre outros. Buscando esti...

Network

Cited By

Projects

Projects (2)
Project
The state of the art in real-time object detection algorithms.
Project
large-scale machine learning, non-convex optimization and high-dimensional data. #AppliedMathematics #LowRank #Sparse #Matrix #Tensor #Decomposition #Factorization #Optimization #DeepLearning #NeuralNetworks