Smart Doorbell Camera Kit v22 - dlib Facial Landmark Drowsiness Detector on Pi 5
Smart Doorbell Camera Kit v22 - Build a Facial Landmark-Based Drowsiness Detector on Raspberry Pi 5
Every part needed, pre-tested for compatibility, with an AI build companion trained on this exact project. Shipped from Bengaluru in 3-5 days.
What if your doorbell could read a visitor's alertness, not just announce their arrival? This kit turns a Raspberry Pi 5 into a doorbell camera that runs a dlib facial landmark detector to calculate real-time eye aspect ratio. When the person at your door shows signs of drowsiness - a classic red flag in security - the system instantly triggers a loud piezo buzzer alarm. You'll deploy deep-learning inference directly on the edge, without needing a cloud connection.
What You'll Build
By the end of the 4-5 hour assembly and coding sessions, you'll have a self-contained unit that sits outside your door. The Pi Camera Module 3 continuously captures frames, the Raspberry Pi 5 runs a pre-optimised dlib shape predictor to extract 68 facial landmarks, and an eye-aspect-ratio calculation runs every few milliseconds. If the EAR drops persistently below your safety threshold, the buzzer sounds - giving you a immediate heads-up that something isn't right at your doorstep. All model inference and logic run locally on the Pi 5; no data ever leaves the board.
What You'll Learn
- Deploy a dlib facial landmark detector on a Raspberry Pi 5 and stream live video from a Pi Camera Module 3
- Calculate eye aspect ratio (EAR) using OpenCV, and set dynamic thresholds to classify drowsiness
- Integrate a piezo buzzer as an alarm actuator driven by a simple GPIO circuit with 220? resistors
- Optimise a computer vision pipeline to run comfortably on the Pi 5's CPU without a separate AI accelerator
Kit Contents
| Component | Quantity |
|---|---|
| Raspberry Pi 5 4GB | 1 |
| Pi Camera Module 3 | 1 |
| Piezo Buzzer | 1 |
| NVMe SSD 128GB | 1 |
| Pi 5 M.2 HAT+ | 1 |
| 220? Resistors | 2 |
| 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
If you're a B.Tech ECE/EEE student tackling a computer vision mini-project, a Smart India Hackathon team prototyping a security solution, or a member of an ATL Tinkering Lab exploring advanced edge AI, this kit fits. It is also ideal for hobbyists at IIT, NIT, VIT or BITS who want to run a real dlib model on a Raspberry Pi 5 and understand every line of code.
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 start a chat with the AI companion - it knows every step and can even generate code snippets. If you still need help, drop us a message on WhatsApp; a human will step in.
Can I adjust the drowsiness sensitivity?
Yes. The eye aspect ratio threshold is a single variable in the Python script. You can raise it for more sensitive detection or lower it to reduce false alarms, all explained in the build guide.
Does the kit include the dlib pre-trained model file?
You'll download the standard shape_predictor_68_face_landmarks.dat directly during the build; the AI companion provides the exact command and even helps you verify the file's integrity.
Is this suitable for real security use?
This project teaches the core principles of edge AI surveillance. While it's primarily an educational tool, many builders harden the code with login alerts and add a relay for a physical siren - the Pi 5 can handle those extensions without extra hardware.
Doorbell Security - dlib facial landmark detector monitors eye aspect ratio on Pi 5 - alarm sounds when drowsiness is detected over threshold.
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