A Deep Learning Based Real-Time Campus Student Movement Detection System
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The project titled “A Deep Learning Based Real-Time Campus Student Movement Detection System” presents an automated and intelligent solution for monitoring and tracking student activities within a campus environment. The system utilizes computer vision and deep learning techniques to detect and recognize student faces in real-time using live video feeds from surveillance cameras. Each video frame is processed to identify faces using a lightweight detection model, and recognized using a deep learning-based feature extraction model. The recognized faces are compared with pre-stored student data in a database, allowing the system to accurately identify individuals and track their movement across different locations. The system is implemented using Python, integrating OpenCV for image processing, TensorFlow Lite for efficient model execution, and Flask for developing a web-based interface for administrators. This approach significantly reduces manual monitoring efforts and enhances campus security by providing continuous and real-time tracking. The system is designed to be efficient, scalable, and user-friendly. Although performance may vary with lighting conditions and camera quality, it provides reliable results under standard conditions. Future enhancements may include multi-camera integration, cloud-based storage, and advanced behavioural analysis. Keywords: Deep Learning, Computer Vision, Face Detection, Face Recognition, Student Tracking, Real-TimeMonitoring, TensorFlow Lite, OpenCV, Flask, Campus Security.
Fields of Study & Subjects
Face recognition and analysis
Video Surveillance and Tracking Methods
Face and Expression Recognition
Publication details
- Journal / source
- International Scientific Journal of Engineering and Management
- Volume
- 05
- Issue
- 03
- Pages
- 1–9
- Publication date
- 30 March 2026
- Language
- EN