之前了解过一些效果较好的跟踪算法，如跟踪人手的HandVu所用的黄金金字塔跟踪、号称可以和三维跟踪媲美的TLD跟踪算法，但现在这个跟踪算法不由为之一振，

只能说牛人太多了啊= =！

The problem is handled using a bag-of-pixels representation and comprises a rigid registration between frames, a segmentation and online appearance learning. The registration compensates for rigid motion, segmentation models any residual shape deformation and the online appearance learning provides continual refinement of both the object and background appearance models. The key to the success of our method is the use of , as opposed to likelihoods.

 

　　

　　

　　

 

• (Published ECC08)
• (Published ECC08)