Principal component pursuit (PCP) is a state-of-the-art approach forbackground estimation problems. Due to their higher computational cost, PCPalgorithms, such as robust principal component analysis (RPCA) and itsvariants, are not feasible in processing high definition videos. To avoid thecurse of dimensionality in those algorithms, several methods have been proposedto solve the background estimation problem in an incremental manner. We proposea batch-incremental background estimation model using a special weightedlow-rank approximation of matrices. Through experiments with real and syntheticvideo sequences, we demonstrate that our method is superior to thestate-of-the-art background estimation algorithms such as GRASTA, ReProCS,incPCP, and GFL.
展开▼
