Surveillance System with Human Intrusion Detection

Abstract

Security in restricted areas is essential for protecting valuable assets, sensitive information, ensuring the safety from intruders. Traditional security systems have many limitations, where they cannot authenticate whether the entered person is an intruder or not. To address this challenge by implementing a real-time face recognition- based surveillance system, is the goal of this project. Realtime Intrusion detection system provides surveillance for restricted and confidential areas with help of face recognition and detection, when an intruder or unauthorized person enters the area, this system will give an alert to the respective in charge through various channels, including email, messaging services, and direct phone calls. In this system, the OpenCV python library along with several algorithms are used to abstract the facial features and to take the input dataset. For face detection, the system utilizes SCRFD and YOLO, and it employs Arcface for accurate face recognition. This technique ensures the system can distinguish between an intruder and an authorized individual entering the secured area. This proactive approach enhances surveillance efficiency and reinforces the safety and integrity of restricted areas. For instance, when an individual enters the restricted area, the system captures and analyses their face. It then verifies whether the detected face matches any authorized faces in the registered user database. If there’s no match, the system identifies the person as an intruder and promptly sends an alert to the designated authority. To enhance accessibility, a user-friendly graphical interface (GUI) has been developed using Python’s Tkinter.