Video Anomaly Detection and Classification for Human Activity Recognition

Abstract

People detection and tracking is one of the important research fields that have gained a lot of attention in the last few years. Although person detection and counting systems are commercially available today, there is a need for further research to address the challenges of scenarios. Automated video surveillance system or Anomaly detection addresses observation of people within a busy environment leading to the description of their actions and interactions. It requires detection and tracking of people to ensure security, safety and site management. Object detection is one of the fundamental steps in Anomaly detection or automated video surveillance. Object detection from the video sequence is mainly performed by background subtraction technique. It is widely used approach for detecting moving objects from static cameras. As the name suggests, background subtraction is the process of separating out the foreground objects from the background in a sequence of video frames. The main aim of the Anomaly detection here is, to detect and track an object in motion by using single video recorded image. Video is recorded and fixed at the database; the background subtraction algorithm is used for segmenting moving object in video. If human entity is detected the tracking lines are formed around human and the object is tracked. The main aim is to develop anomaly detection for real-time security system.