Build a Pi 5 Colour and Shape Sorter Robot with Computer Vision

Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.

Sorting objects by colour and shape is a fundamental task in industrial automation, and this kit lets you build a working miniature conveyor sorter powered by the Raspberry Pi 5. Using OpenCV on the Pi's camera, the system identifies an object’s hue and contour in real time, then triggers two SG90 servos to route it into the correct collection bin. Edge AI is transforming how machines see and decide, and this project puts that power in your hands without any cloud subscription. Whether you're preparing for the Smart India Hackathon, your B.Tech robotics elective, or an ATL Tinkering Lab challenge, this project delivers a real edge AI experience on a compact desk-sized platform.

What You'll Build

You'll assemble a complete vision-guided sorter: a camera module above a small conveyor line captures each object and sends images to the Pi 5, which runs OpenCV algorithms to detect its dominant colour and shape (circle, square, triangle). Based on the classification, servo motors physically divert the object left or right into dedicated bins. The system runs entirely on-device with no cloud dependency, demonstrating true edge AI. After the build, you can easily modify the code to add new shapes or colours, making it an extensible platform for experimentation.

What You'll Learn

• Set up a Raspberry Pi 5 with an M.2 NVMe SSD for fast boot and storage
• Capture and process images using the Pi Camera Module 3 and OpenCV
• Implement real-time colour segmentation and shape contour detection
• Control servo motors with PWM signals to build a mechanical sorting gate

Kit Contents

Why Buy This Kit Instead of Sourcing Parts Separately

Who This Kit Is For

This intermediate-level kit is ideal for engineering students (B.Tech ECE, EEE, CSE) working on computer vision or robotics lab assignments, hackathon teams tackling Smart India Hackathon automation challenges, and ATL Tinkering Lab innovators who have moved beyond basic Arduino projects. CBSE Class 12 students with prior Python experience and an interest in AI/ML will also find it a compelling capstone project. The kit assumes you can read a circuit diagram and edit Python code, but the AI companion fills any gaps.

Built and Backed by Compoden

Every Compoden kit ships with an AI build companion trained on this exact project — accessible via a QR code on the box, with WhatsApp and email backup. We've spent 10 years building projects for makers, schools, and institutions across India. If a part fails because of a manufacturing defect, replace it free within 7 days.