Tracking of Moving Objects Using Morphological Segmentation, Statistical Moments, and Radon Transform

This paper describes real time object tracking of 3D objects in 2D image sequences. The moving objects are segmented by the method of differential image followed by the process of morphological dilation. The moving objects are recognized and tracked using statistical moments. The straight lines in the moving objects are found with the help of Radon transform. The direction of the moving object is calculated from the orientation of the straight lines in the direction of the principal axes of the moving objects. The direction of the moving object and the displacement of the object in the image sequence are used to calculate the velocity of the moving objects. The simulation results of the proposed method are promising on the test images.