Abstract—In many vision based applications moving objects detection and tracking is important and critical task. Because of complicated occlusions and disordered background, identifying moving objects and their tracking is a challenging problem for many computer vision applications. In this paper a new tracking method that uses both Gaussian Mixture Model (GMM) and Optical Flow approach is proposed. Background subtraction is the fast way to detect moving object which subtracts foreground from background. Background subtraction is based on GMM and the tracking of detected object is carried out by Optical Flow model. There are two types of Optical Flow methods i.e., 1) Lucas-Kanade and2) Horn-schunck. In this paper Horn-Schunck model is implemented for tracking a moving object. Both GMM and Optical Flow methods can complement each other and results successful in tracking of objects.

Index Terms—Object detection, Object tracking, Gaussian Mixture model, Optical Flow, Horn- Schunck Model

Cite: A Melody Suzan and G Prathibha, "DETECTION AND TRACKING OF MOVING OBJECTS USING HYBRID MODEL (GMM & HORN-SCHUNCK)," International Journal of Electrical and Electronic Engineering & Telecommunications, Vol. 6, No. 2, pp. 37-42, April 2017.