A Smart Campus System for Locating Missing Persons and Items is proposed to address the challenges of manually monitoring large volumes of surveillance video in academic environments. Traditional methods rely heavily on human observation, which is time-consuming and prone to error. The proposed system leverages deep learning and computer vision techniques to automate the detection and identification process using a reference image. By extracting key features such as shape, color, texture, and patterns, the system compares these with features from live or recorded video feeds. Advanced object detection and face recognition models are employed to identify potential matches, which are then evaluated using similarity measures such as Euclidean distance or cosine similarity. Upon detecting a positive match, the system generates real-time alerts through an interactive user interface. This approach significantly enhances efficiency, reduces manual effort, and improves detection accuracy, making it a scalable, reliable, and effective solution for smart campuses and public safety applications.

Keywords— Smart Campus, Computer Vision, Deep Learning, Image Recognition, Object Detection, Surveillance Systems, Feature Extraction, Similarity Matching, Real-Time Monitoring