Moving Object Detection Based on Fuzzy Color Histogram Features and Dynamic Threshold Optimization

Abstract

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