Smart Surveillance System for Anomaly Recognition

Situation awareness is the key to security. Surveillance systems are installed in all places where security very important. Manually observing surveillance footage captured a monotonous and time consuming task. Security can be defined different terms conditions like violence detection, theft identification, detecting harmful activities etc. In crowded public term covers almost type of unusual events. To eliminate tedious manual we have developed smart which will detect an anomaly alert user authority without any human interference. It critical issue system instantly anomalous behaviour video system. this project, unified framework based on deep neural network proposed activities. This consists (a) object detection module, (b) discriminator tracking (c) activity module recurrent network. The web application apply for three services namely motion fall applicable monitoring environment homes, roads, offices, schools, shops, On notify responsible regarding through mail with detected frame attachment.