Affiliation:
1. Department of Computer Science and Engineering, AMET University, Chennai, India.
Abstract
This work proposes a method for detecting and tracking moving objects that rely onthe partial differential
equation technique and can track both forward and backward. In order to reduce the amount of noise in the output video,
it is first divided into many frames and then pre-processed using methods for the Gaussian filters. The transfer function is
calculated on the binarized frames following the acquisition of the absolute difference for forward tracking and backward
tracking. The forward and backward tracking outputs are combined at the object tracking step to get the desired outcome.
Statistics like f-measure, accuracy, retention, and precision are used to evaluate the predicted technique, and classic
motion detection methods are also used to examine its effectiveness. According to the evaluation results, the suggested
system is superior to the usual high-accuracy rate techniques.
Subject
Electrical and Electronic Engineering,Computational Theory and Mathematics,Human-Computer Interaction,Computational Mechanics