REAL-TIME CRIME DETECTION IN VIDEO STREAMS USING DEEP LEARNING AND WEB TECHNOLOGIES

The rising rate of criminal incidents in urban regions has intensified the need for robust surveillance systems that can identify suspicious activities in real time. Conventional crime detection approaches depend heavily on manual monitoring of CCTV footage, which is not only labor-intensive but also susceptible to human oversight and inefficiencies, especially in large-scale environments. These traditional systems are limited in their capacity to autonomously recognize and react to abnormal events such as theft, assault, or fire, resulting in delayed responses and compromised public safety. To address these shortcomings, this project introduces a web-based crime detection system built with the Django framework, which utilizes a hybrid Deep Convolutional Neural Network (DCNN) and Recurrent Neural Network (RNN) model. The proposed system analyzes video input by processing video frames using OpenCV and classifying them into specific crime categories. With an impressive performance—accuracy of 99.90%, precision of 99.96%, recall of 99.97%, and F1-score of 99.91%, along with a minimal mean squared error (MSE) of 0.09%—the application provides highly accurate real-time detection. Users can upload videos via a user-friendly interface, while administrators are provided with a dashboard to train models and monitor system performance. This integration of deep learning with web technologies results in an intelligent, scalable, and responsive crime detection platform. Ultimately, this system reduces human intervention, enhances surveillance efficiency, and strengthens safety measures in public areas, offering valuable support to law enforcement and urban security operations.