This paper provides a comprehensive review of background subtraction techniques, which are widely used for detecting moving objects from static camera feeds. The review aims to guide designers in selecting the most suitable method for specific applications by categorizing the methods based on speed, memory requirements, and accuracy. The methods discussed include parametric and non-parametric background density estimates, spatial correlation approaches, and more complex models like mixture of Gaussians and kernel density estimation (KDE). Each method's features, advantages, and limitations are detailed, and a performance analysis is presented to help readers understand the trade-offs between different techniques. The review concludes by highlighting the strengths of each method, such as the simplicity and high frame rate of running Gaussian average and median filters, the high accuracy of mixture of Gaussians and KDE, and the spatial correlation capabilities of cooccurrence of image variations and eigenbackgrounds.This paper provides a comprehensive review of background subtraction techniques, which are widely used for detecting moving objects from static camera feeds. The review aims to guide designers in selecting the most suitable method for specific applications by categorizing the methods based on speed, memory requirements, and accuracy. The methods discussed include parametric and non-parametric background density estimates, spatial correlation approaches, and more complex models like mixture of Gaussians and kernel density estimation (KDE). Each method's features, advantages, and limitations are detailed, and a performance analysis is presented to help readers understand the trade-offs between different techniques. The review concludes by highlighting the strengths of each method, such as the simplicity and high frame rate of running Gaussian average and median filters, the high accuracy of mixture of Gaussians and KDE, and the spatial correlation capabilities of cooccurrence of image variations and eigenbackgrounds.