Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
AI Virtual Mouse Controller
Control your computer cursor with hand gestures using just a webcam. This talk demonstrates real-time hand tracking for cursor movement, clicks, and scrolling, with an emphasis on intuitive UX.
AI Virtual Mouse Controller: controla o cursor via gestos da mão, zero hardware extra — só webcam. Stack: Python, OpenCV, MediaPipe pra tracking de mão em tempo real. Demo ao vivo: gestos controlando cursor, click, scroll, sem mouse físico. Mostro código + arquitetura de detecção de landmarks → tradução pra coordenadas de tela.
This Python project implements a real-time, webcam-based virtual mouse controller using MediaPipe for hand landmark detection and PyAutoGUI for cursor manipulation, offering gestural input without extra hardware.
This open-source project provides a real-time AI virtual mouse controller using MediaPipe for gesture recognition and ModernGL for a holographic overlay, enabling OS control via hand movements.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- MediaPipeGoogle's open-source, cross-platform framework for building and deploying real-time machine learning pipelines across mobile, web, and edge devices.MediaPipe is a powerful, open-source framework from Google for applied machine learning (ML). It enables developers to construct complex, multimodal pipelines using a graph-based dataflow model: data moves through connected 'Calculators' for efficient, real-time processing of video, audio, and text . The core strength is its cross-platform capability: build once, and deploy seamlessly across Android, iOS, web (JavaScript), desktop, and IoT devices (like Coral) . MediaPipe offers ready-to-use 'Solutions' (Tasks) for critical computer vision applications, including Face Detection, Hand Tracking, and Pose Estimation (detecting 33 key body points) . This streamlined approach accelerates ML integration, minimizing the need for extensive model tuning or infrastructure setup .
- OpenCVOpenCV (Open Source Computer Vision Library) is the world’s largest, Apache 2-licensed library for real-time computer vision and machine learning.OpenCV is the definitive, cross-platform library for computer vision, packing over 2500 optimized algorithms for tasks like object detection, 3D reconstruction, and image processing. It’s built on C++ but offers robust interfaces for Python, Java, and MATLAB, supporting real-time applications across Windows, Linux, macOS, and mobile platforms. Originally an Intel initiative, it’s now managed by the non-profit Open Source Vision Foundation. With over 40 million estimated monthly downloads, it’s the go-to tool for major companies (Google, Microsoft, IBM) and startups alike, driving everything from automated surveillance to advanced robotics.
- PyAutoGUIPyAutoGUI is the cross-platform Python module that programmatically controls your mouse, keyboard, and screen, automating desktop GUI interactions.PyAutoGUI is a powerful, cross-platform (Windows, macOS, Linux) GUI automation library for Python. It allows scripts to simulate user actions: precisely controlling the mouse with functions like `pyautogui.moveTo(x, y)` and managing keyboard input via `pyautogui.typewrite('text')` or using `hotkey()` for shortcuts (e.g., Ctrl-C). Beyond basic input, the module includes robust screenshot capabilities and image recognition (e.g., `locateOnScreen('button.png')`) to find UI elements, enabling reliable automation for repetitive tasks like data entry, software testing, or bot creation. It's built for efficiency, though users should note the default 0.1-second pause between calls and the critical fail-safe feature.
- NumPyNumPy is the fundamental Python package for high-performance scientific computing, centered on the powerful N-dimensional array object (ndarray).NumPy (Numerical Python) is the foundational library for scientific computing in Python, providing the core `ndarray` (N-dimensional array) object . This object is a homogeneous, fixed-size container that enables highly efficient, vectorized operations: often up to 50x faster than standard Python lists for large datasets . The library includes a comprehensive collection of routines for fast array manipulation, including linear algebra, Fourier transforms, and random simulation . Its performance advantage stems from its core being optimized C and C++ code , establishing it as the universal data structure for data exchange across the entire Python scientific computing ecosystem.
Related talks
More from the community
AI Voice activated Shop Assistant
São Paulo
Cortical Eval
São Paulo
Making easy to the final user
São Paulo
Explore how AI assistants on WhatsApp are revolutionizing customer service for small medical and dental offices, aesthetic clinics,…
Soma Vital — Da obrigação ao cuidado | Soma Vital — From Compliance to Care
São Paulo
VOXMAP - Painel de diálogo - Analisador de Sentimentos
São Paulo
DSPy + Visão computacional
São Paulo
Explore como combinar DSPy com visão computacional para criar agentes de IA mais eficazes, demonstrando um novo conceito…
Compose Email
Loading recent emails...