Self-Directed Tracking of Objects using Deep Learning Technique

Abstract

Security has become a necessity. Asking humans to keep watch for long hours is a cumbersome task and increases the chance of error. Thus, to assist human operators in identifying important events, Automatic Object Tracking is proposed. Firstly, an object is tracked by detecting the object using any of the various object detection methods in frames present in the input video. These methods use the spatial domain, temporal changes, presence, etc., of the objects present. Everything is then tracked using any of the various techniques. This can be used for monitoring traffic, animation, robot vision, and video surveillance. In the proposed system, YOLO v2 is being used for Object Detection, and Kalman Filter and Non-Maximum Suppression will be used for Automatic Object Tracking.