cv

PhD Student and Research Associate

Universidad Rey Juan Carlos

Perception for autonomous driving, focusing on RGB, LiDAR, and fusion-based semantic segmentation for scene understanding in off-road environments.

Optical Team Lead

SEDDI

Responsible for overseeing the daily operations of a small team of R&D engineers, focusing on planning, reviewing, and delivering complex computer vision projects. These projects leveraged advanced, deep learning-based solutions. Alongside my leadership duties, I maintained an active role in the development process, ensuring hands-on involvement from concept to implementation.

Computer Vision Engineer

SEDDI

As a computer vision engineer at SEDDI, I contributed to the development of its flagship product, textura.ai, from its inception. Joining the company at a very early stage allowed me to be involved in every step of the process. I contributed to designing a complex multi-camera and multi-illumination digital material acquisition setup, developed tools to extract textile properties using both classic computer vision and deep learning methods, and implemented solutions for color constancy and calibration across various imaging devices.

Immersive Video Researcher

Nokia Bell Labs

As an immersive video researcher, my internship primarily focused on the field of Human-Computer Interaction, specifically on developing user interfaces based on hand gesture recognition. Additionally, I became familiar with augmented, mixed, and virtual reality concepts and techniques.

Computer Vision Engineer

Bosch

As a machine vision engineer intern, I provided support to the Process Engineering Department by engaging in a variety of tasks. These included studying Data Matrix reading systems and optical lenses, as well as developing an optical calculator. Additionally, I diagnosed and designed computer vision systems and developed computer vision applications with Neurocheck.

Volunteer

SEO/BirdLife

Mentor

Google Summer of Code

Software Developer

JdeRobot

Doctor of Philosophy - PhD

Universidad Rey Juan Carlos

Computer vision

Master's degree

URJC

Computer Vision

Erasmus +

Óbuda University

Electrical Engineering

Bachelor's degree

Universidad Rey Juan Carlos

Audiovisual and Multimedia Systems Engineering

Cross-dataset Evaluation of Visual Semantic Segmentation Models for Off-Road Autonomous Driving

Expert Systems with Applications

Intelligent autonomous driving in off-road environments is an emerging field with great potential to impact areas such as agriculture, forestry, and rescue operations. Perception in these scenarios presents unique challenges due to the diversity of elements and weather conditions, along with the inherent ambiguity in class definitions. Consequently, off-road visual semantic segmentation datasets remain underdeveloped, roughly ten times smaller than their urban counterparts, hindering dependable performance assessment and potentially compromising the safety of autonomous systems. To address these challenges, we present a comprehensive cross-dataset evaluation of visual semantic segmentation models for autonomous off-road navigation. We propose a unified ontology that harmonizes class definitions across relevant datasets, enabling their combination for both training and testing. This approach ensures fair model comparisons and reliable assessment of generalization to unseen domains. We further benchmark models on the original datasets, analyze the impact of different ontology harmonization criteria and conversion strategies, and evaluate the trade-off between segmentation performance and computational cost. Results show that Transformer-based architectures achieve the most consistent segmentation performance across datasets. While often computationally demanding, some variants maintain real-time inference (≈12 ms) with top-tier accuracy. The unified ontology simplifies the segmentation task, yielding more reliable models and about 40% faster training convergence. Cross-dataset training further enhances generalization, improving mean IoU by up to +20% on RUGD and +13% on WildScenes compared to RELLIS-3D-only training. Overall, this study provides valuable insights for developing robust perception modules for off-road autonomous vehicles.

Efficient 3D human pose estimation from RGBD sensors

Displays

Human pose estimation is a core component in applications for which some level of human–computer interaction is required, such as assistive robotics, ambient assisted living or the motion capture systems used in biomechanics or video games production. In this paper, we propose an end-to-end pipeline for estimating 3D human poses that works in real-time in an off-the-shelf computer, using as input video sequences captured with a commercial RGBD sensor. Our hybrid approach is composed of two stages: 2D pose estimation using deep neural networks and 3D registration, for which a lightweight algorithm based on classic computer vision techniques has been developed. We compare several 2D pose estimators and validate the performance of our proposed method against the state-of-the-art, using as benchmark an international and publicly available dataset. Our 2D to 3D registration module alone can reach frame rates of up to 99 fps, while achieving an average error per joint of 132 mm. Furthermore, the proposed solution is agnostic to the model used for 2D pose estimation and can be upgraded with new upcoming solutions or adapted for different articulated objects.