Barcelona Artificial Intelligence Lab
Welcome to reallity, we will not make a better world.
In an effort to equip future doctorate students with valuable skills in the fields of Computer Vision and Natural Language Processing (NLP), I conducted a hands-on training course at the University of Vigo. This course was designed to be practical and accessible, providing participants with a strong foundation in Deep Learning. The course primarily was …
At INSA University, I lead a Master’s program in Data Intelligence and Big Data. This year-long program is conducted in English and focuses on providing students with practical skills in Data Science, Machine Learning, and Deep Learning. Using tools such as Google Colab and Python, the program is designed to offer a hands-on learning experience. …
SiliconBased, a pioneering company based in Tarragona, embarked on a Proof of Concept (POC) that promises to transform the way hydrocarbon transport handles loading and unloading processes. At its core, this innovative project leverages the power of deep learning and computer vision to enhance safety and efficiency. A customized dataset was meticulously crafted to accommodate …
I have developed a deep learning project that predicts the panels to be used by a comic book reader. It is designed for Whakoom, a company that is building the Netflix of comics. Leveraging the work of labelers, we have created a model using over 200k labeled panels, which has significantly increased the efficiency of …
A very complex project and I can’t explain too much due to its uniqueness. A great industrial innovation company hired me because they are building a big enhancement to 5D ultrasounds. It consists in a process of face-detection and beautification. A process of automatisation (and improve) what companies are doing with filters and face apps …
Monitoring wastewater treatment plants with AI has been one of the most successful projects from the innovation area of Veolia group. For this purpose we build custom datasets of segmentation of different problems and test instance and semantic segmentation architectures until we find the more efficient models in external conditions monitoring water 24/7. Lighting changes …
Updata.ca is a company from Québec that hired me for trying different architectures in their solution to classify waste recycling. I was in charge of testing instance segmentation models and they had a dataset of tens of millions images (artificially created). We trained models for days in 2 A100 (40Gb) cluster but results were not …
This was project was difficult! It involved 360º images, equirectangular panoramas and plenty of epipolar geometric concepts to stitch images and find common points between different rooms of the houses. CreoTour is an startup that offer virtual tours services and they contact me to dramatically reduce the time of building a complete virtual tour. As …
To collaborate with the local authorities in the organisation of beaches and access to touristic sites I build different pipelines that counts people or density occupation in the beaches. I also counted anchored boats and tied up in harbours. Images came from CCTV cameras and computation on the edge was necessary to avoid privacy violation. …
One of the biggest challenges in CV is counting people on videos. This due to the difficulties of tracking the same person every frame. Ladorian is a targeted marketing company that has a service to show targeted ads in TVs or screen walls, they were interested in counting people passing in front and looking at …