Hidden Markov Model (HMM) is an important probabilistic model of sequential data processing and statistical study. It has already been successfully applied in many projects in practice. Firstly, this paper introduces the basic principles of the Hidden Markov Model, and then gives a review to its latest application in the human activity analysis, network security and information extraction. Finally it summarizes the theory and latest progress of the recently proposed infinite Hidden Markov Model (iHMM).