Skip to Main Content
This paper addresses real time feature tracking when the frame-to-frame motion is large in the video. To solve this problem, we first estimate the locally piecewise, translational motion by matching the horizontal and vertical characteristic curves of the consecutive images. Then, we incorporate the motion estimates into the pyramidal Kanade-Lucas-Tomasi (KLT) feature tracker to accomplish the tracking task. To compute the motion estimates efficiently and effectively, we use dynamic programming to minimize the cost function. These motion estimates will serve as the coarse motion at the deepest pyramid level which makes the residual motion small enough such that the feature tracker can work well. In addition, we introduce a feature rejection method that improves the efficiency. Experiments show that our method can make the feature tracker suitable to track features with large motion.