![]() |
|
||
Online Graph-Based TrackingHyeonseob Nam, Seunghoon Hong, and Bohyung Han Department of Computer Science and Engineering, POSTECH, Koreanamhs09@postech.ac.kr maga33@postech.ac.kr bhhan@postech.ac.kr Abstract. Tracking by sequential Bayesian filtering relies on a graphical model with temporally ordered linear structure based on temporal smoothness assumption. This framework is convenient to propagate the posterior through the first-order Markov chain. However, density propagation from a single immediately preceding frame may be unreliable especially in challenging situations such as abrupt appearance changes, fast motion, occlusion, and so on. We propose a visual tracking algorithm based on more general graphical models, where multiple previous frames contribute to computing the posterior in the current frame and edges between frames are created upon inter-frame trackability. Such data-driven graphical model reflects sequence structures as well as target characteristics, and is more desirable to implement a robust tracking algorithm. The proposed tracking algorithm runs online and achieves outstanding performance with respect to the state-of-the-art trackers. We illustrate quantitative and qualitative performance of our algorithm in all the sequences in tracking benchmark and other challenging videos. Keywords: Online tracking, Bayesian model averaging, patch matching LNCS 8693, p. 112 ff. lncs@springer.com
|