Figure 2From: AUTO GMM-SAMT: An Automatic Object Tracking System for Video Surveillance in Traffic ScenariosA frame of sequence Parking_lot and the corresponding detection results of the proposed method compared to the traditional method. First row: original frame (a) and background estimated by the proposed method with temporal dependency (α0 = 0.001, s = 10, umin = 15) (b). Bottom row: standard method with α = 0.001 (c) and α = 0.01(d).Back to article page