Home / Projects / K.I.V.E
DIPLOMA PROJECT // HTL BRAUNAU // OPEN RESEARCH

K.I.V.E
Künstliche Intelligenz zur Verkehrszeichenerkennung

// AI-Powered Traffic Sign Recognition for Visually Impaired People

A smartphone application using a custom-trained neural network to detect and announce traffic signs, pedestrian crossings, and traffic lights in real time — giving visually impaired people independent, safe navigation of road environments.

Year
2021
Type
Diploma Project
School
HTL Braunau
Awards
2 × 1st Place
🏆 AQUILA 2021 — 1st Place 🏅 UNIKATE — Award + €2,000 🎓 HTL Braunau Diploma ♿ Accessibility Focus
Swift iOS App Python PyTorch Computer Vision Object Detection Audio Feedback Distance Estimation Custom Dataset
2
Major Awards
AQUILA + UNIKATE
€2,500
Prize Money
+ €500 safety training
3
Team Members
HTL Braunau ETI
~90%
Detection Rate
Reliable accuracy
Real-time
Processing
On-device inference
01 // OVERVIEW

The Problem We Solved

For visually impaired pedestrians, navigating traffic environments is a daily challenge. Existing assistive technology focuses mostly on obstacle detection — but traffic signs, crossing lights, and pedestrian zones are equally critical and largely ignored by consumer-grade assistive tech.

K.I.V.E was our diploma project at HTL Braunau — a year-long deep dive into training a custom computer vision model specifically for Austrian traffic signage and pedestrian infrastructure. We collaborated directly with visually impaired testers throughout development to ensure the output was genuinely useful, not just technically impressive.

The system uses the smartphone camera as a sensor, processes frames through a custom-trained object detection model, and delivers spatial audio announcements through the phone speaker or earphones — telling the user not just what was detected, but how far away it is and whether it requires immediate action.

Project NameK.I.V.E
Full TitleKünstliche Intelligenz zur
Verkehrszeichenerkennung
InstitutionHTL Braunau am Inn
DepartmentElektronik und technische Informatik
Schwerpunkt: Communications
SupervisorProf. Kurt Kreilinger
Year2020 – 2021
Target UsersVisually impaired pedestrians
02 // SYSTEM DESIGN

How It Works

01
📷
Camera Capture
The app continuously captures frames from the smartphone camera at a fixed interval, optimised for real-world walking speed and processing latency.
02
🧠
AI Inference
Each frame is passed through the custom-trained object detection model. The network classifies detected objects and returns bounding boxes with confidence scores.
03
📐
Distance Estimation
Using bounding box dimensions relative to known object sizes, the system estimates the real-world distance to each detected object with reliable precision.
04
🔊
Audio Output
High-priority detections trigger an immediate speech announcement: the object type and estimated distance. Output via speaker or earphones, works without looking at the screen.
03 // DETECTION CLASSES

What The AI Detects

🚦
Traffic Lights
Red / green state detection, distance and phase announcement
🦓
Pedestrian Crossing
Zebra crossing detection, direction and distance to crossing
🚶
Pedestrian Signals
Dedicated pedestrian traffic light detection (Ampelmännchen)
🚫
Stop Signs
Priority and hazard signs relevant to pedestrian safety
⚠️
Warning Signs
School zones, construction areas, pedestrian hazard zones
ℹ️
Info Signs
Pedestrian-relevant information signs and direction markings
KIVE — System Architecture
┌────────────────────────────────────────────────────────┐
│                  SMARTPHONE APP                        │
├────────────┬──────────────────────┬────────────────────┤
  Camera      AI Inference Engine   Audio Output      
  Module      ────────────────────  ──────────────────
  live        Custom model          TTS speech synth  
  frames      Bounding boxes        Distance announce 
  → frames    Confidence score      Priority filter   
             Class labels          Speaker / earphone
└────────────┴──────────────────────┴────────────────────┘

Detection flow:
  Frame → [Preprocessing]  [Model Inference]  [Distance Calc]
   [Priority Filter]  [Audio Announce]

Example outputs:
  "Red traffic light, approximately 4 metres ahead"
  "Pedestrian crossing detected, 6 metres to your left"
  "Green pedestrian signal, safe to cross"
04 // RECOGNITION

Awards & Prizes

October 2021
UNIKAT Award
Österreichischer Behindertenrat (Austrian Disability Council)
€2,000 Prize Money
Selected as "UNIKAT" — only fully completed, production-ready projects qualify. The project was tested live at the award ceremony by visually impaired participants, who provided positive feedback on real-world usability. The jury praised the accessibility focus, completeness, and practical impact.
June 2021
AQUILA 2021 — 1st Place
Kuratorium für Verkehrssicherheit (KFV) — Austrian Road Safety Prize
€500 Safety Training + Trophy
Awarded first place in the "Secondary Schools" category at Austria's premier road safety competition. An interdisciplinary jury evaluated entries on creativity, innovation, accident-reduction potential, sustainability, and practical applicability. KIVE topped the category on all criteria.
05 // TEAM

The Project Team

👨‍💻
Marco Nagl
Developer
HTL Braunau — Electronics & Technical CS
→ That's me
👨‍💻
Kilian Feix
Developer
HTL Braunau — Electronics & Technical CS
👨‍💻
Matthias Vöcklinger
Developer
HTL Braunau — Electronics & Technical CS
👨‍🏫
Kurt Kreilinger
Project Supervisor
HTL Braunau — Faculty

All three team members are graduates of HTL Braunau's Elektronik und technische Informatik department, with the autonomous focus area "Communications". The project was completed as the compulsory diploma thesis (Diplomarbeit) in the final year of the five-year programme.

06 // PRESS COVERAGE

In The News

HTL Braunau
KIVE als UNIKAT ausgezeichnet
Official school coverage of the UNIKATE award — €2,000 prize money from the Austrian Disability Council, October 2021.
HTL Braunau
KIVE siegt beim AQUILA 2021
Coverage of the first-place win at Austria's road safety competition, awarded by the KFV (Kuratorium für Verkehrssicherheit), June 2021.
meinbezirk.at
KIVE wird zu UNIKAT
Regional news coverage in the Braunau district portal about the UNIKATE award and the project's impact on accessibility in Austria.