. "RIV/68407700:21230/12:00200611" . . "P(GBP103/12/G084)" . . . . "RIV/68407700:21230/12:00200611!RIV13-GA0-21230___" . "The paper presents contributions to the design of the Flock of Trackers (FoT). The FoT trackers estimate the pose of the tracked object by robustly combining displacement estimates from a subset of predicted local trackers that cover the object. The first contribution, called the Cell FoT, allows local trackers to drift to points good to track. The Cell FoT was compared with the Kalal et al. Grid FoT and outperformed it on all sequences but one and for all local failure prediction methods. As a second contribution, we introduce two new predictors of local tracker failure - the neighbourhood consistency predictor (Nh) and the Markov predictor (Mp) and show that the new predictors combined with the normalized cross-correlation (NCC) predictor are more powerful and almost two times faster than the predictor based on normalized cross-correlation (NCC) and forward-backward procedure (FB). The resulting tracker equipped with the new predictors combined with the normalized cross-correlation predictor was compared with state-of-the-art tracking algorithms and surpassed them in terms of the number of sequences where a given tracking algorithm performed best." . "Matas, Ji\u0159\u00ED" . . "Voj\u00ED\u0159, Tom\u00E1\u0161" . . . . . . "[53A0F6BDA7E6]" . . . . "Increasing Robustness of the Flock of Trackers" . "tracking; predictors; flock"@en . . "2"^^ . "Increasing Robustness of the Flock of Trackers"@en . . "21230" . . "2"^^ . "141127" . "The paper presents contributions to the design of the Flock of Trackers (FoT). The FoT trackers estimate the pose of the tracked object by robustly combining displacement estimates from a subset of predicted local trackers that cover the object. The first contribution, called the Cell FoT, allows local trackers to drift to points good to track. The Cell FoT was compared with the Kalal et al. Grid FoT and outperformed it on all sequences but one and for all local failure prediction methods. As a second contribution, we introduce two new predictors of local tracker failure - the neighbourhood consistency predictor (Nh) and the Markov predictor (Mp) and show that the new predictors combined with the normalized cross-correlation (NCC) predictor are more powerful and almost two times faster than the predictor based on normalized cross-correlation (NCC) and forward-backward procedure (FB). The resulting tracker equipped with the new predictors combined with the normalized cross-correlation predictor was compared with state-of-the-art tracking algorithms and surpassed them in terms of the number of sequences where a given tracking algorithm performed best."@en . "Increasing Robustness of the Flock of Trackers" . "Increasing Robustness of the Flock of Trackers"@en .