Welcome to my research space

Fredy Barrientos-Espillco, Ph.D.

|

Translating cutting-edge Deep Learning and Computer Vision research into robust, real-world autonomous navigation and environmental monitoring systems.

View Publications Get In Touch

Core Details

Degree Ph.D. in Computer Science (Summa Cum Laude)
University Complutense University of Madrid
Email
Office Physics - Room 237
Scroll Down

Biography & Focus

Hi! I’m Fredy Barrientos-Espillco, an **Applied AI Researcher** specialized in Deep Learning, Computer Vision, and Generative Models.

I completed my Ph.D. in Computer Science at the Complutense University of Madrid (2020–2025), where I was awarded **Summa Cum Laude**. I was advised by Professor Gonzalo Pajares and Eva Besada. My research centers around designing deep learning algorithms for object detection, semantic segmentation, and generative models, with direct applications in autonomous navigation and environmental monitoring.

I have led key research lines within high-impact R&D projects funded by the Spanish Government and the European Union. Currently, I am focused on the exciting synergies between Computer Vision and Large Language Models (LLMs) to tackle next-generation multimodal challenges.

Key Research Contributions

  • Multi-Task CNN Architectures: Designing joint detection and segmentation networks optimized for complex and dynamic aquatic environments.
  • Diffusion Models Customization: Fine-tuning text-to-image models (SDXL) combined with LLM-assisted prompt engineering to generate high-quality synthetic training data.
  • ASV Visual Perception: Developing real-time, lightweight visual perception algorithms for Autonomous Surface Vehicles (ASVs) navigating under challenging scenarios.

Selected Publications

My recent papers in top-tier journals such as Expert Systems with Applications, Applied Soft Computing, and Neural Networks.

Expert Systems with Applications August 2025

Customization of the Text-to-Image Diffusion Model by Fine-Tuning for the generation of synthetic images of cyanobacterial blooms in lentic water bodies

F. Barrientos-Espillco, G. Pajares, J.A. López-Orozco, E. Besada-Portas

Presents a novel approach combining DreamBooth-based fine-tuning of the Stable Diffusion XL model with LLM-driven prompt generation (LLaMa 2) to synthesize realistic images of cyanobacterial blooms and navigational obstacles for training visual models.

Read Paper
Applied Soft Computing September 2024

Integration of object detection and semantic segmentation based on Convolutional Neural Networks for navigation and monitoring of cyanobacterial blooms in lentic water scenes

F. Barrientos-Espillco, M.J. Gómez-Silva, E. Besada-Portas, G. Pajares

Introduces a unified CNN architecture that simultaneously handles object detection and pixel-level semantic segmentation in aquatic environments, enabling safer autonomous boat navigation.

Read Paper
Neural Networks January 2024

Filter Pruning for Convolutional Neural Networks in Semantic Image Segmentation

C. I. López-González, E. Gascó, F. Barrientos-Espillco, E. Besada-Portas, G. Pajares

Proposes filter pruning and optimization strategies for semantic segmentation CNNs, allowing heavy models to run in real-time on resource-constrained edge devices aboard ASVs.

Read Paper
Applied Soft Computing July 2023

Semantic segmentation based on Deep learning for the detection of Cyanobacterial Harmful Algal Blooms (CyanoHABs) using synthetic images

F. Barrientos-Espillco, E. Gascó, C.I. López-González, M.J. Gómez-Silva, G. Pajares

Develops a deep learning semantic segmentation pipeline to detect harmful algal blooms using synthetic imagery to alleviate the lack of real annotated training datasets.

Read Paper

Research Projects

Principal R&D lines funded by the European Union and the Spanish Government.

INSERTION

Inspection and maintenance in harsh environments by multi-robot cooperation

2022 - 2025 PID2021-127648OB-C33

A collaborative project with UPO, UPM, and UCM to develop advanced techniques for perception, localization, mapping, navigation, and multi-robot cooperation in challenging environments.

SMART-BLOOMS

Intelligent management of cyanobacteria using digital twins and edge computing

2022 - 2024 TED2021-130123B-I00

Ecological & Digital Transition project focused on creating a digital twin of dammed water reservoirs and an IoT infrastructure with edge computing to manage and predict cyanobacterial blooms.

IA-GES BLOOM-CM

Comprehensive system for cyanobacterial bloom alert and management

2021 - 2024 Community of Madrid (Y2020/TCS-6420)

Created an early warning IoT framework using AI-guided Autonomous Surface Vehicles (ASVs) combined with modeling and simulation techniques to map inland water blooms.

AMPBAS

Automatic Monitoring of Pollutants in Dammed Waters using Biosensors & ASVs

2019 - 2021 RTI2018-098962-B-C21

R&D challenges project delivering a cooperative multi-boat platform equipped with biological sensors to detect and alert on bacterial and chemical water contamination.

Skills & Expertise

Research Focus

Computer Vision Deep Learning Generative Models Semantic Segmentation Object Detection Image Synthesis Model Compression / Pruning Autonomous Surface Vehicles (ASVs)

Programming

Python Java C++ MATLAB JavaScript HTML5 / CSS3

Frameworks & Tools

PyTorch TensorFlow Keras OpenCV scikit-learn NumPy / Pandas DreamBooth / SDXL Git / Linux / Docker

Get In Touch

Open for research collaborations, consulting, or speaking engagements.

Email

fredybar@ucm.es

Phone

(+34) 91 394 4375

Office Location

Physics Building - Room 237
Complutense University of Madrid

Other Activities

Regular reviewer for high-impact journals in the fields of Computer Vision, Deep Learning, and Generative AI.

Email copied to clipboard!