In this study, a Monte-Carlo-based algorithm, named CRF, was developed for generating background images from a video sequence. This algorithm is a variant of the Teknomo-Fernandez (TF) algorithm, an efficient background generation algorithm that also incorporates the Monte-Carlo concept and applies simple logical bit operations. Two different configurations of CRF were implemented, i.e. CRF9,2 and CRF81,1. A brute force algorithm that generates the ground truth using modal pixel bit values was also developed in order to analyze the empirical performances of the TF algorithm and the 2 CRF configurations. Experiments on some colored video tests show that the CRF configurations outperform the TF algorithm in terms of accuracy. However, the TF algorithm remains more efficient in terms of processing time.
展开▼
