Surveillance System Using Machine Learning
Kirtesh Suryawanshi · International Journal for Research in Applied Science and Engineering Technology · 2025
This paper presents a novel machine learning-based surveillance system designed to detect human movements, estimate the number of individuals, and analyse their timing with high precision. The proposed system leverages advanced computer vision techniques and Machine learning algorithms to process video data in real time. By utilizing [specific ML models, e.g., YOLO or CNN-based architectures], the system accurately identifies human activities, tracks individuals, and provides detailed insights into movement patterns. Experimental evaluations conducted on [specific dataset, e.g., MOT or COCO] demonstrate the system's effectiveness, achieving an accuracy of [X%] in human detection and [Y%] in counting individuals. Additionally, the system excels in timing analysis, making it suitable for applications in security, crowd management, and behavioural monitoring. The results highlight the potential of the proposed approach to address challenges in traditional surveillance systems, offering a robust and scalable solution for real-world