SENSOR BASED ANOMALY DETECTION SYSTEM FOR SMART JUNCTIONS

Abstract: The project “Sensor based anomaly Detection System for Smart Junctions” has been developed using C#.Net as front end and SQL server as backend. The project helps to identify the Burglar movement activities and process from CCTV video footage. In a large video surveillance setup, there can easily be thousands of cameras. Constantly monitoring all this video for suspicious behavior is a very resource-consuming task. In some setups, it is however mission critical that this is done. It could for instance be needed in order for a guard to be able to take action on an incident with as little delay as possible. To limit the resources needed to do this monitoring, it would be helpful if the video surveillance system itself, by analyzing the video, could somehow generate a warning if something suspicious or at least abnormal is happening. For identifying the anomaly, the user needs to monitor the video regularly. In such application the proposed anomaly detection model can be applied to effectively identify and creates alerts about the anomaly. The main purpose of this project Monitoring scheme of anomaly will helps to improve the efficiency of the alert mechanism and also identifying the suspected entry. And its provide Automatic Alert system. This can be implemented to any kind of video monitoring application such as road safety, anolomoly movement monitoring applications. The system need some initial training in order to understand what is normal and what is not. This desktop application can implement high level monitoring places.

Keywords: Road safety, Anomaly, Video Surveillance, Alert System, Sensors, Cameras, Smart Junctions.