Version 1 — Eligibility & anti-theft
Face + plate verification for disability-support vehicles and other restricted fleets. Intended early customers: P2G and sectors that need proof the rightful driver is the one using the car.

Graduation Project · 2026
DVD
Edge AI that stops ineligible drivers from using protected vehicles — and protects passengers when trips turn dangerous.
Purpose
Egypt supports people with disabilities with vehicles imported at heavily reduced customs cost. That relief has been exploited — traders and intermediaries manipulate beneficiaries, and ineligible drivers end up using the cars. Digital Verified Driver starts here: verify who is behind the wheel against authorized records, and reduce unauthorized use and theft.
A second, stronger path watches inside the cabin and along the route — detecting violence, harassment-related events, and accidents for ride-hailing fleets and student transport.
Market
Two product paths. Two customer realities.
Face + plate verification for disability-support vehicles and other restricted fleets. Intended early customers: P2G and sectors that need proof the rightful driver is the one using the car.
Cabin and route monitoring for platforms like Uber — where violence and harassment during trips are a rising concern in Egypt — and for international schools protecting students in buses and critical campus locations.
System
Raspberry Pi, IP camera, and LCD for real-time face + plate checks against authorized vehicle records — built to stop ineligible use and support anti-theft workflows.
Dual camera modules plus GSM/GPS for in-cabin monitoring — violence, harassment signals, accidents — with owner and operations alerts and live vehicle location.
512-D embeddings, plate compare, multi-driver plates, JWT roles, MongoDB database dvd.
Local 7″ touch UI plus web dashboard — live violations, evidence, trips, map, and Email/Telegram alerts.
Capabilities
Face match against driver_faces. Full match or face_only when plate text is empty and PLATE_STRICT=false.
No server EasyOCR. Plate YOLO → Char YOLO → CNN OCR on device; server cleans and compares.
wrong_driver, wrong_plate_owner, no_face_detected, no_plate_detected — with decision metadata.
Accident, violence, and harassment-related events with image, confidence, device id, and map coordinates — for roadside and in-cabin paths.
Person registration (photo / JSON / manual embedding), trip log, audit log, access requests.
Email and Telegram on serious violations and high-confidence road alerts.
Architecture
Collections include users, persons, driver_faces, checks, violations, incidents, devices, vehicles, and audit_logs — served through a JWT-protected dashboard with public Pi endpoints for check-driver, incidents, and heartbeat.
Hardware
Modular embedded stack from the graduation design — processing, vision, comms, storage, HMI, and emergency input.
Compute
Main processing unit for vision pipelines, peripherals, and software logic. Quad-core Cortex-A76 up to 2.4 GHz, 16 GB LPDDR4X, Wi-Fi/Bluetooth, Gigabit Ethernet, 40-pin GPIO.
IP camera
2MP Mini Fixed Bullet for surroundings and plates. 1080p@30 fps, 4.0 mm lens, Smart IR to 30 m, H.265/H.264, PoE, IP67, RTSP streaming to the Pi.
CSI camera
OV5647 module on CSI for driver face and plate frames — primary visual input for detection, identification, and verification.
Comms + GPS
Quad-band GSM/GPRS with integrated GPS over UART. Sends SMS/location alerts on unauthorized use and supports real-time vehicle tracking.
Storage
microSDXC UHS-I (up to 140 MB/s) for OS, models, captured images, and configuration on continuous edge workloads.
Power
USB-C 5 V / 5 A (~27 W) regulated supply for stable capture and inference with cameras and modules attached.
HMI
1024×600 capacitive display (up to 5-point touch) for local real-time violation output; pairs with the remote web dashboard for logs and evidence.
Emergency
GPIO momentary switch that pulls GPS location and posts it to the web platform for accidents, medical, or security emergencies.
Auxiliary
Cooling fan for sustained Pi load; camera housing for mechanical protection and stable optical alignment.
Evaluated, not adopted
T-A7608SA-H (ESP32 + 4G/GPS) — capable, but costlier than SIM808; ESP32 unused with Pi as host. STEVAL-ASTRA1B — strong AI/IoT candidate, unavailable in the Egyptian market during build.
Edge intelligence

Recognition
Real awards and competition milestones for this graduation project — no invented wins.
2026
Electrical Engineering Division — Engineers Syndicate forum recognition for Digital Verified Driver.
Aug 2026
Shortlisted for the Under 30 Bootcamp 2026 and Final Pitch at Zewail City (9–12 August 2026) — reached the last stage; did not win the prize.
2026
Hardware grant to build the Digital Verified Driver prototype.
2026
Selected for technical support to develop an advanced AI/IoT system.
2026
Innovators Care Fund financial funding for the graduation project.
Dec 2025
Athar Accelerator & Plan International Egypt — product concept under mentorship.
Product


Build journal
Enclosure design, modular print-ready parts, and assembly studies from the graduation build.










Next
Available for AI engineering engagements in Canada, Saudi Arabia, and worldwide.