Smolic, A.A.SmolicMakai, B.B.MakaiSikora, T.T.Sikora2022-03-032022-03-031999https://publica.fraunhofer.de/handle/publica/19631210.1109/76.7520932-s2.0-0033099050We present two recursive methods for the real-time estimation of long-term three-dimensional (3-D) motion parameters from monocular image sequences suitable for synthetic/natural hybrid coding face animation and model-based coding applications. Based on feature point extractions in energy frame, the 3-D motion parameters of a human face are estimated with a predictive approach. The first method uses a recursive linear least squares approach and the second employs a nonlinear extended Kalman filter, which does not rely on a linearized model of the face motion. Both methods perform a prediction and correction loop at every time step. Compared to other methods described in the literature, the recursive and predictive structure of the proposed estimation process solves the pencomputer animationfeature extractionfiltering theoryimage codingimage sequenceskalman filtersleast squares approximationsmotion estimationnonlinear filtersprediction theoryrecursive estimationlong-term 3d motion parameterssnhc face animationmodel-based coding applicationsreal-time estimationmonocular image sequencessynthetic/natural hybrid codingfeature point extractionenergy framepredictive approachrecursive linear least squaresnonlinear extended kalman filtercorrection loopprediction looperror accumulationlong-term motion estimationexperimental resultssynthetic datareal image sequences621journal article