Visual Object Tracking Using Fuzzy-based Thresholdingand Kalman Filter

of movement and detection of objects are important branches of image processing and computer vision due to their promising applications such as robotics, industrial automation and the military. In this paper, we propose a new approach for visual object tracking using fuzzy-based thresholding and Kalman filter. In the proposed algorithm, knowledge of three different thresholding methods (i.e. mode method, iterative thresholding and double thresholding) is used to create " if-then " fuzzy rules. The designed fuzzy-based thresholding method combines the mentioned three different thresholds in order to provide the appropriate threshold which will be utilized to segment the object from the background. Finally, the segmented frame is applied to a Kalman filter to predict the next path when the object moves. To evaluate the effectiveness of the proposed method, we compared the obtained position of the object based on the proposed method with the results of the gravity center method and also their real positions. The experimental results show that the proposed approach can improve the tracking stabilization when objects go across complex backgrounds.