Description

Introduction
This project aims to design and implement a full-stack web system for detecting and
documenting illegal construction using aerial imagery and AI analysis. Two student teams
will develop the core system, dedicated to AI-based analysis and classification of
construction anomalies. The system will process drone imagery, detect changes, classify
them by severity, and store all data in an accessible format for decision-makers.

Background
Illegal construction is a significant challenge for municipal and governmental authorities
worldwide. Detecting, verifying, and acting on construction violations is often a long and
resource-intensive process, further complicated by legal challenges in proving evidence. The
proposed solution integrates three advanced components: drones for rapid area scanning,
AI for real-time analysis, and high-quality 3D documentation. This combination enables
accurate and efficient detection of construction anomalies.

Project Scope
The AI team will develop machine learning models capable of analyzing drone imagery to
detect irregular or illegal construction, classify anomalies by severity, and integrate results
into the web system in real time, while ensuring accuracy, explainability, and scalability of
the models.

Student Requirements
• Knowledge in machine learning and computer vision (any model)
• Ability to design and train models for object detection, change detection and classification.
• Strong problem-solving skills and ability to optimize models for real-time performance.

Development Tools
• Python
• AI Processing Libraries: OpenCV, NumPy, Pandas, Requests, PyTorch/YOLO, Scikit-learn,
paho-mqtt.
• Hardware Communication: LoRa (gateway)
• Additional Tools: Postman, GitHub, VSCode
Deliverables
• Illegal Construction Detection ai model – analyze drone imagery to detect and
highlight illegal construction or irregular changes in buildings and land use.
• YouTube video
• Poster
• Presentation
• GitHub link to the code

AI Team – Illegal Construction Detection

AI and Machine Learning

Description

Emphasis in project execution

The project is has cooperation with the industry and combines meeting deadlines while being creative and focused on the task