Abstract:
Abnormal activity detection is crucial in surveillance. To record anomalous behavior, automatic video capture is needed. Our Intelligent Video Surveillance System uses deep learning to detect video abnormalities. The system can detect actions in real time and save video frames as images for the user to view.
Activity recognition models with computationally sophisticated classifiers make aberrant activity responses slow. An effective Spatial autoencoder will detect aberrant human activity in the surveillance stream.
This system detects irregular footage or real-time activity like violence or theft. You can upload a video from your device for detection. It can also detect real-time activity. Detection begins with a camera button press. Video frames will be recorded as images if abnormalities are detected.
The front-end uses HTML, CSS, and JavaScript, and the back-end uses Python. Django and MySQL are used. This study employed Avenue Dataset for abnormal event and UCSD anomaly detection. The Spatial Autoencoder model is used.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
