A Novel Approach to Robust Background Subtraction

摘要

Nowadays, background model does not have any robust solution and constitutes one of the main problems in surveillance systems. Researchers work in several approaches in order to get better background pixel models. This is a previous step to apply the background subtraction technique and results are not as good as people expect. We propose a novel approach to the background subtraction technique without a strong dependence of the background pixel model. We compare our algorithm versus Wallflower algorithm [1]. We use the standards deviation of the difference as an independent initial parameter to reach an adjusted threshold for every moment. This solution is more efficient computationally than the wallflower approach.