AI Postal Scale Kit - ESP32 Camera SKU Detection & MQTT Totals
Build an AI-Powered Postal Scale That Sees and Totals Packages
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
Step into a logistics laboratory with a single kit. You’ll assemble a smart postal scale that uses a camera, a quantised YOLOv5 model running on an ESP32-S3, and an industrial load cell to recognise SKU items placed on a pad and automatically tally a cart’s total weight and value via MQTT. It’s an end-to-end embedded machine learning system, ready to transform the way packages are sorted in small warehouses, campus mailrooms, or hackathon prototypes.
What You'll Build
You’ll build a standalone device that captures a top-down image of any item placed on its weighing platform, identifies it from a trained SKU database (labels like “book”, “electronics”, “spare part”), records its measured weight, and pushes a cart entry to an MQTT broker. The 1.8-inch TFT display shows live weight, recognised SKU, and the running tally. A microSD card logs every transaction with timestamps from the DS3231 RTC for later auditing. The device is powered by a stable 5V supply and enclosed in a project box you can mount at a shipping counter.
What You'll Learn
- Deploy a quantised YOLOv5 object detection model on an ESP32-S3 with TensorFlow Lite Micro
- Integrate an OV2640 camera and optimize image capture for consistent inference
- Interface an HX711 load cell amplifier to measure precise weight and calibrate offset/scale factors
- Implement MQTT communication to transmit cart updates to a local broker or cloud dashboard
Kit Contents
| Component | Quantity |
|---|---|
| ESP32-S3 Dev Board | 1 |
| OV2640 Camera Module | 1 |
| HX711 + 5kg Load Cell | 1 |
| DS3231 RTC | 1 |
| MicroSD Module | 1 |
| 1.8in TFT ST7735 | 1 |
| LM2596 Buck Converter | 1 |
| 1000µF 25V Caps | 2 |
| 100nF Caps | 15 |
| PCB Prototype Board | 3 |
| Enclosure Box | 1 |
| 5V 3A PSU | 1 |
| Soldering Iron | 1 |
| Solder Wire | 1 |
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
Engineers and researchers building prototypes for Smart India Hackathon logistics tracks, B.Tech ECE/EEE final-year projects, or startup MVPs in warehouse automation. If you’re tackling edge AI deployment in a constrained environment and need a ready-to-assemble reference design, this kit gets you from unboxing to inference in a weekend. It’s also a fit for IIT/NIT/VIT/BITS students exploring on-device vision and MQTT integration.
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?
Scan the QR code to chat with the AI companion, or WhatsApp us directly. We’ll walk you through wiring checks, calibration steps, and model deployment errors.
Can I use this scale in a live small warehouse setting?
Yes, the prototype is robust enough for low-volume operations. The 5kg load cell handles typical parcel weights, and the model can be retrained with your own SKU images.
How accurate is the SKU recognition?
With a fine-tuned YOLOv5n model running on ESP32-S3, you can expect over 90% accuracy under stable lighting. Calibration and light shielding improve consistency.
Does the kit include trained SKU models?
You’ll get a demo model pre-trained on common parcel types. The AI companion guides you through collecting your own images and training a custom model on your laptop.
Logistics — OV2640 + YOLOv5 quantised model on ESP32-S3 identifies SKU items placed on pad. Totals cart via MQTT.
What's in this kit
- ESP32-S3 Dev Board
- OV2640 Camera Module
- HX711 + 5kg Load Cell
- DS3231 RTC
- MicroSD Module
- 1.8in TFT ST7735
- LM2596 Buck Converter
- 1000µF 25V Caps x2
- 100nF Caps x15
- PCB Prototype Board x3
- Enclosure Box
- 5V 3A PSU
- Soldering Iron
- Solder Wire
Choose your assembly option:
- Soldering Kit — 25W soldering iron, 60/40 solder wire, flux, and small perfboard for permanent assembly.
- Breadboard Combo — 800-point full-size breadboard with 65-piece jumper wire pack for solderless prototyping.
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