Real-time UHD background modelling with mixed selection block updates

The vast majority of foreground detection methods require heavy hardware optimization to process in real-time standard definition videos. Indeed, those methods process the whole frame for the detection but also for the background modelling part which makes them resourceguzzlers (time, memory, etc.) unable to be applied to Ultra High Definition (UHD) videos. This paper presents a real-time background modelling method called Mixed Block Background Modelling (MBBM). It is a spatio-temporal approach which updates the background model by carefully selecting block by a linear and pseudo-random orders and update the corresponding model's block parts. The two block selection orders make sure that every block will be updated. For foreground detection purposes, the method is combined with a foreground detection designed for UHD videos such as the Adaptive Block-Propagative Background Subtraction method. Experimental results show that the proposed MBBM can process 50 min. of 4K UHD videos in less than 6 hours. while other methods are estimated to take from 8 days to more than 21 years. Compared to 10 stateof-the-art foreground detection methods, the proposed MBBM shows the best quality results with an average global quality score of 0.597 (1 being the maximum) on a dataset of 4K UHDTV sequences containing various situation like illumination variation. Finally, the processing time per pixel of the MBBM is the lowest of all compared methods with an average of 3.18×10^-8 s.