This study aims to estimate a Block Time-Varying channel by identifying its key parameters using a limited number of pilots occupying a subset of transmitted symbols. The method is evaluated in the context of an Orthogonal Time-Frequency Space (OTFS) system, proposing two estimators for different levels of available information. The first, based on received signals, employs Maximum Likelihood (ML) with a four-dimensional grid search, simplified to two dimensions via a linear model reformulation. The second estimator incorporates prior knowledge of parameter transitions using the Extended Kalman Filter (EKF). Performance is evaluated against theoretical lower bounds.