Knowing the current phenological state of an agricultural crop is a powerful tool for precision farming applications. In the past, it has been estimated with remote sensing data by exploiting time series of Normalised Difference Vegetation Index (NDVI), but always at the end of the campaign and only providing results for some key states. In this work, a new dynamical framework is proposed to provide real-time estimates in a continuous range of states, for which NDVI images are combined with a prediction model in an optimal way using a particle filter. The methodology is tested over a set of 8 to 13 rice parcels during 2008–2013, achieving a high determination factor R 2 = 0.93 ( n = 379 ) for the complete phenological range. This method is also used to predict the end of season date, obtaining a high accuracy with an anticipation of around 40–60 days. Among the key advantages of this approach, phenology is estimated each time a new observation is available, hence enabling the potential detection of anomalies in real-time during the cultivation. In addition, the estimation procedure is robust in the case of noisy observations, and it is not limited to a few phenological stages.