Real-Time Visual Tracking Based on an Appearance Model and a Motion Mode

Abstract. Object tracking is a challenging problem in computer vision commu-nity. It is very difficult to solve it efficiently due to the appearance or motion changes of the object, such as pose, occlusion, or illumination. Existing online tracking algorithms often update models with samples from observations in re-cent frames. And some successful tracking algorithms use more complex mod-els to make the performance better. But most of them take a long time to detect the object. In this paper, we proposed an effective and efficient tracking algo-rithm with an appearance model based on features extracted from the multi-scale image feature space with data-independent basis and a motion mode based on Gaussian perturbation. In addition, the features used in our approach are compressed in a small vector, making the classifier more efficient. The motion model based on random Gaussian distribution makes the performance more ef-fective. The proposed algorithm runs in real-time and performs very well against some existing algorithms on challenging sequences