Real-Time Human Activity Detection Using Deep Learning

In recent years, the demand for intelligent surveillance systems has increased due to rising security concerns. This paper presents a real-time human activity detection system using deep learning techniques. The system classifies activities as normal or abnormal using video data. Frames are extracted from videos and processed using computer vision techniques. A Convolutional Neural Network (CNN) model is trained to recognize patterns and classify activities accurately. The system also provides real-time predictions and alerts for abnormal activities. A user-friendly web interface is developed using Streamlit to display results. The proposed system achieves good accuracy and can be used in real-world surveillance applications.