👋 Welcome to VisionSort-RPi Docs

🎯 An intelligent edge-deployed conveyor belt system powered by Raspberry Pi 5, YOLOv8, and the Hailo AI accelerator — designed to detect and sort bolts & nuts in real time.

📜 Navigation


🌟 Project Highlights


📂 Documentation Sections

🧠 Overview

Summary of the project, design philosophy, and objectives.

🧰 Setup Guide

Setup the environment using Hailo’s official RPi repo:


git clone https://github.com/hailo-ai/hailo-rpi5-examples.git
cd hailo-rpi5-examples
./install.sh
source setup_env.sh

Then run the system:


python detection/detection.py \
  --labels-json resources/nut_bolt-labels.json \
  --hef-path model/nut_bolt_model.hef \
  --input rpi

🧱 Mechanical Components & CAD

This project includes custom-designed mechanical components modeled in Creo Parametric and fabricated using 3D printing. Key components include:

🔗 View CAD designs & prints in CAD/
📄 Download full BOM: BOM.xlsx
📤 External CAD repo: GrabCAD – VisionSort-RPi

📦 Download 3D printable CAD models:
➡️ GitHub Release: CAD v1.0

⚙️ Hardware Wiring

Details on how GPIO pins are used to control motors and servos.

See: Wiring_Setup.pdf

📦 Model Training & Conversion

🖼️ System Visualization

3D CAD Model
CAD Model
Real Conveyor System
Real System

📽️ Demo & Results

🎥 Watch the real-time bolt & nut sorting demo on YouTube



👨‍💻 About the Author

Rohiith Gettala — MSc Robotics Engineer passionate about real-time vision systems, embedded AI, and building things that move and think 🤖
📬 Email | LinkedIn