Today, tracking of moving objects in video becomes a highlight in multimedia. This paper proposes a novel method, which is suitable for applying on relatively high-resolution videos that moving objects can be distinguished from their color and shape information. This method matches and tracks multiple moving objects in video by extracting and combining multi-features. With the background reconstruction method we proposed, the moving objects are separated as sub images from the background, we first extract some valuable features from each sub image, especially the topological information. Then, features are applied to a strong classifier which is accumulated with weak feature classifiers. After that, by the initial matching of moving objects, we extract their kinematical features to reinforce the matching method. Finally, experimental results show the effectiveness of the novel algorithm.