Last page update: 06/03/2023
I am a Ph.D. holder in Computer Vision and Machine Learning, with over 20 years of professional experience in software engineering, software architecture, and software design.
I am currently the Head of AI at ActiveEon, Paris, France, where I lead a team of Ph.Ds in Artificial Intelligence (AI) and Machine Learning.
My expertise lies in computer vision, with a specialization in object detection, segmentation, and tracking, as well as event/action recognition and behavior classification/prediction.
As a Computer Vision Specialist with more than 10 years of experience, I am skilled in both C++ and Python programming languages. I am a proactive problem solver with a keen ability to self-learn and keep up with the latest technologies in my field.
In my current role, I focus on the intersection of scientific research and software engineering to bring cutting-edge AI technologies to the core platform of ActiveEon. My main areas of focus are AI at Scale, HPC+IA, and MLOps.
My team and I have been developing the Proactive AI Orchestration platform since 2017, which has helped customers automate and orchestrate AI-based workflows at scale, with parallel and distributed execution.
As the Head of AI, I am responsible for defining the AI roadmap, supporting team members, and driving key AI projects. My activities include end-to-end AI product design, architecture, and operation, as well as the development of large-scale AI workflows.
I have also developed a Distributed AutoML tool for large-scale hyperparameter optimization and neural architecture search, as well as the Proactive Python SDK and Jupyter Kernel for submitting runtime dynamic AI workflows.
My doctoral research focused on advanced matrix and tensor methods for robust low-rank/sparse representation and subspace learning of multidimensional and streaming data, such as moving object detection and background-foreground separation in multi-spectral and multi-featured video sequences.
Additionally, I have deployed computer vision and machine learning models at the edge on system-on-a-chip (SoC) devices such as Raspberry PI, PandaBoard, and NVIDIA Jetson boards.
Prior to my current role, I worked on several embedded systems and robotic projects between my B.Sc. and M.Sc.
I have also peer-reviewed for several high-quality journals and reviewed for international conferences/workshops.
Main research interests: Computer Vision, Machine / Deep Learning, Pattern Recognition, Applied Mathematics, Matrix / Tensor Decomposition, Optimization, Big Data.
Journal reviewer: I peer-reviewed for more than 10 high-quality journals, such as Elsevier (CVIU, IVC, PRL, NC, IF), Springer (NCA, CC, FITEE, JIVP), IEEE (TIP, TNNLS, TCSVT), MDPI (Sensors), JEI, JOSA-A, PLOS ONE. For more information, please see my Publons profile for an updated version.
My open source libraries and source code:
BGSLibrary - A Background Subtraction Library.
VDTC - Vehicle Detection, Tracking, and Counting.
LRSLibrary - Low-Rank and Sparse tools for Background Modeling and Subtraction in Videos.
MTT - Matlab Tensor Tools for Computer Vision.
IMTSL - Incremental and Multi-feature Tensor Subspace Learning.
OSTD - Online Stochastic Tensor Decomposition.
For more details, please visit my GitHub profile: https://github.com/andrewssobral