Retail Footfall Camera Kit v37
Raspberry Pi 5 Retail Footfall Camera Kit: Build an Edge AI Analytics System with Ollama & CLIP
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
Transform a Raspberry Pi 5 into a privacy-first retail footfall camera that combines a local large language model with CLIP image embeddings. This advanced edge AI system queries a knowledge base using both text and images — entirely offline, with no cloud dependencies. Ideal for engineering students and AI enthusiasts wanting to build production-grade analytics.
What You'll Build
You'll assemble a camera system that captures footfall data in a shop, processes it locally using an Ollama LLM and CLIP embeddings stored on NVMe, and then query that database with natural language or image prompts. For example, ask "How many people wore red shirts today?" or show an image of a customer to retrieve their last visit.
What You'll Learn
- Set up NVMe SSD on Raspberry Pi 5 for high-speed edge AI inference
- Deploy Ollama LLM locally and fine-tune for retail queries
- Generate and store CLIP image embeddings from Pi Camera Module 3
- Integrate an I2S MEMS microphone for voice-based querying
Kit Contents
| Component | Quantity |
|---|---|
| Raspberry Pi 5 8GB | 1 |
| NVMe SSD 512GB | 1 |
| Pi 5 M.2 HAT+ | 1 |
| Pi Camera Module 3 | 1 |
| INMP441 I2S Mic | 1 |
| USB-C PSU | 1 |
| M-M Wires | 10 |
Why Buy This Kit Instead of Sourcing Parts Separately
| Factor | Sourcing Separately | Compoden Kit |
|---|---|---|
| Compatibility checks | You verify every part | Pre-tested as a system |
| Build support | Forums and scattered tutorials | AI companion trained on this exact project |
| Time to first working build | Days of debugging | Hours, with step-by-step guidance |
| Shipping coordination | Multiple sellers, multiple delays | One shipment from Bengaluru in 3-5 days |
Who This Kit Is For
This kit suits final-year B.Tech ECE and CS students building IoT or AI capstone projects. It’s also ideal for Smart India Hackathon participants focusing on retail tech, and IIT/NIT/BITS teams prototyping edge analytics. Startup founders can prototype privacy-compliant footfall analytics without cloud costs.
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.
What if I get stuck during the build?
Our AI build companion, accessible via QR code on the box, walks you through every step. You can also reach us on WhatsApp for human support.
Can I run this system without an internet connection?
Yes, the Ollama LLM and CLIP model run entirely locally. You only need internet for initial setup and package downloads.
How accurate is the footfall detection?
Accuracy depends on lighting and camera placement, but with proper setup, the CLIP-based system can classify objects reliably. The AI companion guides you on optimal positioning.
What if I need to expand storage for more embeddings?
The included 512GB NVMe SSD provides ample room for thousands of image embeddings. If needed, you can swap to a larger SSD; the Pi 5 M.2 HAT+ supports standard NVMe drives.
Retail Analytics — Ollama LLM + CLIP image embeddings on Pi 5 NVMe — query a local knowledge base using text and image inputs.
What's in this kit
Shipping Information
- Prepaid Orders: ₹75 for orders up to ₹999, FREE shipping above ₹999
- COD Orders: ₹125 shipping + ₹50 COD fee = ₹175 total
- Delivery Timeline: Dispatch in 1-2 days, delivery in 2-7 days depending on location
Returns & Warranty
- 7-Day Return: Manufacturing defects only (approval required)
- Warranty: 7 days from delivery
- Non-Returnable: Batteries, consumables, cut wires, clearance items