AI for Crime Detection

Developed an AI-based video surveillance system capable of detecting suspicious activities and potential crimes in real-time using action recognition techniques. The system analyzes video streams and identifies abnormal human behaviors using 3D Convolutional Neural Networks (3D-CNNs), which capture both spatial and temporal motion patterns.

The model was trained to recognize complex actions across consecutive video frames, enabling early detection of violent or anomalous events. This project integrates Artificial Intelligence with IoT concepts for smart surveillance applications.

Potential applications include:

- Smart city surveillance systems

- Automated threat detection

- Real-time security monitoring

- Industrial and public safety systems

Technologies: Python, 3D CNNs, Deep Learning, Computer Vision, Video Processing