A novel filtering approach for tracking visual objects

Abstract

Visual object tracking of moving objects is a dynamic area of research in computer vision. In developing video surveillance systems, it requires fast, consistent and robust algorithms for poignant object detection, classification, tracking, and activity analysis. Explicitly, tracking of multiple objects is more complicated than single object tracking. This paper suggests an algorithm by using a constant acceleration Kalman filter to track visual objects of variant sizes such as cars, ball and humans by varying few factors. Gaussian Mixture Model (GMM) is used for object detection using background subtraction. A blob analysis is carried for calculating area and centroid of detected objects. Theses, parameters are used for predicting and updating the location of tracked object using a Kalman filter. The proposed Kalman filter uses a constant acceleration model, as it is capable of tracking objects in all possible conditions of occlusions. The occlusion problem is minimized by defining a suitable cost function. Experiments using MATLAB show that the simulated results of proposed algorithm are accurate and can be used for real time multiple visual object tracking.