Miguel Mendez

Bio

I am a Senior Machine Learning Engineer at Hudl, focused on developing cutting-edge computer vision systems for sports analytics. My work involves developing production-scale AI systems for data acquisition and analysis, with expertise in multi-object tracking, camera calibration, object detection, and generative models.

My professional journey includes developing advance computer vision model for automated sports data collection at Statsbomb. Previously, I conducted computer vision research at Gradiant and implementing machine learning solutions for retail optimization at Desigual. I completed my M.Sc. in Artificial Intelligence through a dual program, studying at the Polytechnic University of Catalonia for the first year and Purdue University for my final year. I hold a B.Sc. in Computer Science from the University of A Coruña, which included an enriching exchange year at the University of Stavanger in Norway.

News

• August 2024. Statsbomb have been acquired by Hudl! I am excited to continue working on the future of sports analytics with the Hudl team.

• September 2023. Published a blog post about homography estimation in Statsbomb blog [English, Spanish].

• February 2022. I am joining Statsbomb as a Machine Learning Engineer .

• April 2021. Drone vs Bird paper is out! Check our awarded solution.

• February 2021. We have open sourced Pyodi our Python Object Detecion Insights library.

• September 2020. We have won 2020 Drone vs Bird Detection Challenge.

• September 2019. Paper from IEEE AVSS2019 Drone-vs-Bird Detection Challenge is out.

Posts

• 

  Image Normalization: Comparing CPU vs GPU Performance in PyTorch

  Understanding the performance differences in Pytorch's image normalization

• 

  Httpx vs Aiohttp: Handling High-Concurrency Requests in Async Python

  How switching from httpx to aiohttp resolved my httpx read errors and networking issues

• 

  Understanding Object Tracking Metrics

  Comparing MOTA, IDF1, and HOTA for Multi-Object Tracking Evaluation

• 

  A Guide to Horizontal Pod Autoscaler

  Understand and visualize how Kubernetes HPA works with a real world example

• 

  Exploring Transformer-Based Methods in Video Instance Segmentation

  A comparison of the latest research and innovations in Video Instance Segmentation

• 

  Building an Efficient Docker Image with Poetry and PyTorch

  A guide for your Deep Learning environment setup

See more posts
• 

  Image Registration in Sports Analytics:

  Using computer vision to map NFL images, recover homographies, and locate players in real-world coordinates

• 

  MLFlow Deployment on AWS with Terraform

  A Simple Guide to MLFlow Deployment on Kubernetes

• 

  Multi-Object Tracking by Detection: A Comprehensive Guide

  Exploring the Advancements and Accuracy in Multi-Object Tracking Technologies

• 

  Creating Better Data: AI & Homography Estimation

  The cornerstone of Statsbomb tracking data collection methodology

• 

  Image Transmission for Computer Vision: A Comparison of Torchserve's REST and gRPC

  Benchmarking protocols performance for sending images

• 

  CNNs & Transformers Explainability: What do they see?

  A simple explanation and visualization of ViT attentions and ResNet activations

• 

  Using Ansible and Python to monitor my servers

  Code your own scripts in Python, deploy them using Ansible & Conda and get real time reports from your server

• 

  DVC + MMdetection

  A guide to train, monitor, compare and evaluate your pytorch object detection models

• 

  Export to Github Cache with Docker Buildx

  We can finally use Docker buildx cache-to gha with build-push action and it is blazingly fast!

• 

  Version control your dataset with DVC

  Use DVC and Git for tracking changes on your machine learning dataset

• 

  Reduce Actions time with Docker and Github Cache

  Use Github Actions cache and Docker to reduce time installing Conda dependencies

• 

  Generating FIFA 19 players with VAEs and Tensorflow

  Learn to generate your own footbal players

• 

  VAEs! Generating images with Tensorflow

  Learn how to code a Variational Autoencoder

• 

  The theory behind Variational Autoencoders

  Learn the math

Vitæ

• Vigo, ESP (Remote)

  Aug'24 - now
  

  Senior Machine Learning Engineer - Hudl

• Vigo, ESP (Remote)

  Feb'22 - Jul'24
  

  Machine Learning Engineer - Statsbomb

  Architecting and deploying advanced computer vision systems for automated sports analytics, processing thousands of matches across 90+ leagues. Building custom deep learning models (PyTorch) for real-time player tracking, ball detection, and camera calibration. Established an end-to-end MLOps pipeline for model training, deployment, and monitoring at scale, while leading AI infrastructure modernization and technical initiatives in sports data collection.

• Vigo, ESP

  Apr'19 - Jan'22
  

  Machine Learning Research Engineer - Gradiant

  Led development of computer vision solutions for real-time object detection and semantic segmentation with deep learning frameworks (PyTorch/TensorFlow). Optimized models for deployment on edge (Nvidia Jetson) and cloud platforms (AWS/Azure). Directed AI best practices, MLOps pipelines, and infrastructure modernization.

• Barcelona, ESP

  Feb'18 - Apr'19
  

  Data Scientist, Consultant - Desigual, InnoIT

  Designed end-to-end machine learning solutions for retail optimization, including demand forecasting and intelligent inventory management across a global store network. Developed a CNN-based visual search system for product recommendations and style matching. Implemented predictive analytics to enhance stock distribution and improve supply chain efficiency.

• Indiana, USA

  Aug'16 - Jun'17
  

  Master in Artificial Intelligence (Study Abroad) - Purdue University

  Researcher at Purdue Datalab, collaborating with PhD candidates on AI projects. Specialized in time series analysis and feature engineering, with thesis: Feature Construction and Classification of Time Series Data. Completed advanced coursework in machine learning and data mining.

• Barcelona, ESP

  Sep'15 - Jun'17
  

  Master in Artificial Intelligence - Polytechnic University of Catalonia

  Specialized in computer vision and neural network architectures, with focus on supervised and unsupervised learning methodologies. Core coursework included deep learning, statistical modeling, and pattern recognition. Developed strong foundation in fundamental AI algorithms and their practical applications.

• Stavanger, NOR

  Aug'14 - Jun'14
  

  B.Sc. Student (Study Abroad) - University of Stavanger

  Awarded competitive Erasmus and NILS scholarships for international studies. Completed thesis project on computer vision applications, implementing optical flow algorithms for motion analysis using action camera data. Focus on real-time video processing and computer vision techniques.

• A Coruña, ESP

  Sep'11 - Jun'16
  

  B.Sc. Student - University of A Coruña

  Comprehensive foundation in computer science fundamentals, with focus on algorithmic complexity, data structures, and software development methodologies.

Publications

• Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge

  Sensors: Special Issue Deep Learning Based UAV Detection, Classification, and Tracking

  Coluccia, Angelo and Fascista, Alessio and Schumann, Arne and Sommer, Lars and Dimou, Anastasios and Zarpalas, Dimitrios and Méndez, Miguel and de la Iglesia, David and González, Iago and Mercier, Jean-Philippe and Gagné, Guillaume and Mitra, Arka and Rajashekar, Shobha

• Drone-vs-Bird Detection Challenge at IEEE AVSS2019

  2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

  A. Coluccia and A. Fascista and A. Schumann and L. Sommer and M. Ghenescu and T. Piatrik and G. De Cubber and M. Nalamati and A. Kapoor and M. Saqib and N. Sharma and M. Blumenstein and V. Magoulianitis and D. Ataloglou and A. Dimou and D. Zarpalas and P. Daras and C. Craye and S. Ardjoune and D. De la Iglesia and M. Méndez and R. Dosil and I. González

Other Projects

• Pyodi: Python Object Detection Insights

  A simple tool for explore your object detection dataset. The goal of this library is to provide simple and intuitive visualizations from your dataset and automatically find the best parameters for generating a specific grid of anchors that can fit you data characteristics

  Tags: #deep-learning #computer-vision #object-detection #pytorch