Object Identification Based on Background Subtraction and Morphological Process

Abstract: Background subtraction in dynamic scenes is an important and challenging task. This paper proposes an efficient motion detection system based on background subtraction using fuzzy colour histogram and morphological processing. Here two methods are used effectively for object detection followed by people counting and compare these performance based on accurate estimation. In dynamic texture scenes, morphological process and filtering are used effectively for unwanted pixel removal from the background. We introduce a background subtraction algorithm for temporally dynamic texture scenes using a clustering-based feature, called fuzzy colour histogram (FCH), which has an ability of greatly attenuating colour variations generated by background motions while still highlighting moving objects detection. Experimental results demonstrate that proposed method is effective for motion detection system based on background subtraction using fuzzy colour histogram and morphological processing, compared to several other competitive methods.

Keywords: Background Subtraction, Dynamic texture scenes, Fuzzy colour Histogram, Morphological Processing, Object Detection