Moving object detection using modified GMM based background subtraction

Abstract

Academics have become increasingly interested in creating cutting-edge technologies to enhance Intelligent Video Surveillance (IVS) performance in terms of accuracy, speed, complexity, and deployment. It has been noted that precise object detection is the only way for IVS to function well in higher level applications including event interpretation, tracking, classification, and activity recognition. Through the use of cutting-edge techniques, the current study seeks to improve the performance accuracy of object detection techniques based on Gaussian Mixture Models (GMM). It is achieved by developing crucial phases in the object detecting process. In this study, it is discussed how to model each pixel as a mixture of Gaussians and how to update the model using an online k-means approximation. The adaptive mixture model's Gaussian distributions are then analyzed to identify which ones are more likely to be the product of a background process. Each pixel is categorized according to whether the background model is thought to include the Gaussian distribution that best depicts it.