Skip to content
View Frankl1sales's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report Frankl1sales

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Frankl1sales/README.md


👨‍💻 About Me

I'm currently in the final semester of my Computer Science degree at the Federal University of Pelotas (UFPel). I'm passionate about how computational systems generate, process, and interpret images - especially in the context of video compression and coding.

As a Scientific Initiation Scholar at ViTech (Video Technology Research Group – UFPel), I conduct research on the Versatile Video Coding (VVC) standard, with a focus on optimizing intra-frame coding for 360º videos using machine learning and lightweight models. I'm working toward integrating these methods into the VVC Test Model (VTM). I have also explored Multiple Constant Multiplication (MCM) approaches for DST-VII and DCT-VIII transforms. These efforts have led to publications accepted at events like LASCAS 2025 and WebMedia 2024.

In parallel, I collaborate with the Cybersecurity Research Group and the Veterinary Epidemiology Lab at UFPel, applying AI and NLP to predictive epidemiology and disease historiography, particularly focusing on arboviruses.

Additionally, I work as an Intern in Image Processing and Computer Vision at Primeira Mesa, where I develop applications using:

  • 🟢 YOLO for object detection
  • 🟣 DeepSORT for multi-object tracking
  • 🔵 TensorFlow, PyTorch, and scikit-image for model training and deep learning tasks
  • 🟡 OpenCV, NumPy, and other visual data processing tools

🧪 Current Projects & Interests

  • 🎓 VVC intra prediction for 360º videos
  • 🔬 Lightweight ML models for integration in video encoders
  • 🧠 NLP + AI for health and epidemiological data
  • 🧩 Deep learning for object detection, segmentation, and tracking

🌐 Let's Connect

📫 Feel free to reach out to me:


🛠️ Languages and Tools




📊 GitHub Stats


🧩 3D Contribution Graph

3D Contributions

trophy

Pinned Loading

  1. Estrutura-de-Dados Public

    Implementações baseadas na apostila de Estruturas de Dados dos Profs. Waldemar Celes e José Lucas Rangel (PUC-Rio, 2002).

    C 20

  2. Magalu_Selenium Public

    Código apresentado na cadeira de Engenharia de Software 2

    Python 1

  3. OpenCV_Face_Detection Public

    Este projeto demonstra como utilizar a biblioteca OpenCV para detectar faces e olhos em vídeos em tempo real. Utilizando classificadores em cascata treinados com algoritmos Haar, realizou-se a dete…

    Python

  4. Haskell Public

    Lista de exercícios realizadas durante a aula de Semânticas Formais

    Haskell

  5. VTM360-19.0_Lib13.4_ResultsTCC Public

    Fork Otavio

    C++

  6. Steganography-Aes256-Extraction Public

    Atividade didática de esteganografia com extração e descriptografia de dados ocultos usando steghide e GPG. A mensagem foi protegida com AES256 e as senhas foram deduzidas com base em pistas simples.

    Python