TUM Logo

Physical Intrusion Detection with Raspberry Pi

Physical Intrusion Detection with Raspberry Pi

Supervisor(s): Ching-Yu Kao
Status: finished
Topic: Others
Author: Mohamed Nour Touati
Submission: 2023-05-15
Type of Thesis: Bachelorthesis
Thesis topic in co-operation with the Fraunhofer Institute for Applied and Integrated Security AISEC, Garching

Description

This thesis aims to develop a robust intrusion detection system by
integrating a Raspberry Pi with a camera device and a facial recognition
system. The facial detection component captures images through the
camera of the Raspberry Pi, which are then compared with the images
of authorized personnel in the database using a Siamese neural
network. By implementing this whitelisting approach, the proposed
system has the potential to enhance the accuracy and reliability of
physical intrusion detection. The integration of these components
offers a comprehensive and effective solution for detecting intruders,
thereby improving overall security measures. The attained integrated
system provides the required functionality. Nevertheless, further
improvements can still be incorporated to improve the computational
performance of the integrated system.