Segmenting foreground objects in a multi-modal background using modified Z-score

Abstract

This article presents a background subtraction method to detect moving objects across a stationary camera view. A hybrid pixel representation is presented to minimize the effect of shadow illumination. A non-recursive background model is developed to address the problem with gradual illumination change. Modified Z-score labeling is employed to analyze the sample variation of the temporal sequence to build a multi-modal background. The same measure is further applied to detect the foreground pixels against the stationary background classes. Morphological filtering is employed to suppress the sensor noise as well as to fill the camouflage holes. A decision rule is formulated that considers the period of being stationary of a foreground object and the period of being absence of a background class to tackle the object relocation problem. The proposed approach along with nine other state-of-the-art methods are compared on various image sequences taken from the Wallflower and the I2R datasets in terms of recall, precision, figure of merit, and percentage of correct classification. The tabular results, as well as the obtained figures demonstrate the efficacy of the proposed scheme over its counterparts.