Moving Object Detection Using Eigen Background In Comparison with Gaussian Mixture Model to measure F-Score

The main objective of this work is to compare the accuracy and F-Score of the Eigen backdrop's motion object detection to that of the Gaussian Mixture Model (GMM) and assess how poorly it performs in these areas. The CDNet dataset, which consists of video clips, provided samples. Clincalc is used to calculate samples by setting parameters such alpha (0.3), minimum pretest power (80%), and error rate (0.05). The accuracy and F-score of the Eigen Background subtraction algorithm in detecting moving objects are compared with that of the Gaussian Mixture Model.In comparison to the Gaussian Mixture Model's accuracy (83.84<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>) and F-score (79.16), Eigen background exhibits higher accuracy (86.8<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>) and F-score (80.91). When comparing photos with different levels of brightness, the accuracy of the brighter images is better. The Eigen background Subtraction's accuracy and F-score are found to be much greater than those of the Gaussian Mixture Model.