Development of Campus Security Surveillance System Using Smart Device

Abstract

The Smart Campus Surveillance-Based Guidance System uses cutting-edge surveillance technologies to improve student safety and direction on college campuses. To improve services, decision-making, and sustainability, our solution combines physical infrastructure with smart technologies. Our research attempts to solve the issue of students getting lost, wandering around campus, and missing classes all of which can result in social and academic issues. The system uses a real-time guidance system to track students' movements and direct them to their appropriate classrooms. As computer vision and machine learning have advanced, active security surveillance and object detection have emerged as essential elements of contemporary security systems. Public areas, transit hubs, and vital infrastructure are just a few of the settings where these systems are intended to improve real-time monitoring and danger identification. Active security surveillance systems look for possible security risks, illegal activity, or irregularities by continuously scanning and analyzing sensor data or video feeds. By using sophisticated algorithms for motion detection, facial recognition, and behavioral analysis, they enable the quick identification of questionable activity or people. One of these systems' essential components, object detection, entails recognizing and categorizing the objects in a scene. Usually, deep learning methods like convolutional neural networks (CNNs), which can precisely identify and classify items like cars, weapons, or unattended baggage, are used to accomplish this.