Foreground Object Segmentation in Dynamic Background Scenarios

摘要

In the paper research on foreground object segmentation in dynamic background scenarios (i.e. flowing water, moving leaves or shrubs) is described. The effectiveness of different algorithms: based on FIFO sample buffer, singlevariant, multi-variant (MOG, Clustering) and recently proposed ViBE and PBAS is evaluated. A post-processing method, that allows false detections reduction is also proposed. The solution was tested on sequences from the changedetection.net dataset. The obtained results indicate usefulness of the proposed approach.