Code Monkey home page Code Monkey logo

👋 Welcome! My name is Israel. I am a machine perception enthusiast with research and industry experience in the fields of Machine Learning, Computer Vision, and Robotics. Currently, I work as a Software Engineer at Sony in Brussels. Previously, I completed my M.Sc. in Artificial Intelligence at KU Leuven with a thesis in collaboration with the European Space Agency. My research interests include machine perception, models on the edge, and 3D computer vision. In particular, I would like to explore the use of commodity sensors for democratizing real-time 3D scene reconstruction and understanding.

As a Software Engineer in the AI & Perception team at the Mobile and Exploration Department in Sony Depthsensing Solutions NV in Brussels-Belgium, I work on the challenging topic of achieving real-time depth completion on edge devices. In a nutshell, my team's objective is to combine RGB data and highly sparse depth information to produce a dense and accurate depth map stream in real-time on a mobile device. I am primarily involved in model optimization, implementing of latency-aware structured pruning designed to jointly optimize for latency and accuracy in TensorFlow.

🔥 News

  • 2023.10 🎉 My team is showcasing our Neural RGB-D Fusion technology at at ICCV2023 🎉
  • 2022.10 I joined AI & Perception team at Sony Depthsensing Solutions NV in Brussels, Belgium
  • 2022.09 I graduated with Summa cum laude distinctions from the M.Sc. in Artificial Intelligence at KU Leuven

📝 Publications

  • I. R. Tiñini Alvarez, I. Perez, T. Wiese, L. Bielenberg, and R. Detry, “Sample-Tube Pose Estimation Based on Two- Stage Approach for Fetching on Mars Surface,“ 16th Symposium on Advanced Space Technologies in Robotics and Automation, Netherlands, 2022
  • I. R. Tiñini Alvarez, G. Sahonero–Alvarez, C. Menacho and J. Suarez, “Exploring Edge Computing for Gait Recog- nition,“ 4th International Conference on Bio-Engineering for Smart Technologies, France, 2021. î
  • I. R. Tiñini Alvarez and G. Sahonero-Alvarez, “Cross-View Gait Recognition Based on U-Net,“ International Joint Conference on Neural Networks, United Kingdom, 2020. î
  • I. R. Tiñini Alvarez and G. Sahonero-Alvarez, “Gait Recognition Based on Modified Gait Energy Image,“ IEEE Sciences and Humanities International Research Conference, Peru, 201

🎖 Honors and Awards

  • 2022.09 KU Leuven Summa Cum Laude graduation distinction
  • 2021.09 First runner-up in the National Science and Technology Competition.
  • 2020.08 Research award grant, under the ”Pequeños Proyectos de Investigación” program.
  • 2018.09 UCB Summa Cum Laude graduation award

📖 Education

  • 2022.09 M.S. in Artificial Intelligence at KU Leuven | Summa cum laude distinction | Thesis: 6D pose estimation for autonomous sample collection on Mars at the European Space Agency
  • 2020.08 Graduate specialization in Machine Learning
  • 2020.01 Graduate specialization in Robotics
  • 2019.09 Graduate specialization in Education
  • 2018.09 B.S. in Mechatronics at UCB | Summa cum laude distinction | Thesis: Appearance-based gait recognition approach for automatic surveillance systems at CIDIMEC

Israel Raul Tiñini Alvarez's Projects

crossviewgait icon crossviewgait

In this work, we propose a method of gait recognition using a conditional generative model to generate view-invariant features and overcome appearance variations due to changes of clothing, carrying conditions, and view angle.

kul icon kul

documents and files from KUL

labelme icon labelme

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

mybot icon mybot

The objective of this project is to implement a navigation system based on ROS for the control of a terrestrial robot that performs autonomous localization and navigation tasks.

raft icon raft

fork for training and inference experimentation and benchmarking

tf-raft icon tf-raft

RAFT (Recurrent All Pairs Field Transforms for Optical Flow) implementation via tf.keras

ucbsquirrels icon ucbsquirrels

This repository contains the material developed by the UCB-Squirrels team for the OpenCV 2021 Spatial AI competition. It is written in Python3 and uses depthai to interact with the OAKs.

vision4cities icon vision4cities

This project aims to develop an intelligent device to count the passengers on a bus using computer vision techniques.

workshop_cvwithml icon workshop_cvwithml

This is the material used to present the Computer Vision with Machine Learning Workshop at UCB

yolov3-opencvdnn icon yolov3-opencvdnn

This repository is about my first code for object detection using OpenCV DNN module and YOLOv3 algorithm.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.