Maintaining discipline and security in places like exam rooms, libraries, corporate offices, and guarded government buildings has become extremely difficult due to the growing usage of smartphones. Conventional surveillance systems mostly rely on human monitoring, which is frequently erratic, time-consuming, and prone to error. This paper introduces Phone Patrol, an intelligent surveillance system that uses computer vision and deep learning techniques to automatically detect mobile phone usage in limited regions in order to overcome these restrictions. In order to determine whether mobile phones are present in the monitored area, the suggested system analyses real-time video feeds taken by security cameras and uses an object detection model. To guarantee prompt detection and reaction, the system incorporates automated alarm mechanisms, model inference, and image preparation. The framework offers a dependable and scalable way to enforce mobile-free regulations by reducing human intervention and improving monitoring accuracy. The practical viability of using the system in real-world scenarios is highlighted by experimental evaluation, which shows efficient detection performance under various illumination and climatic circumstances. The suggested strategy advances AI-driven surveillance technology with the goal of enhancing operational integrity and institutional security.
Mahesh et al. (Sun,) studied this question.