The recognition of the guidance law of a non-cooperative target vehicle is very useful for the counteraction design of the pursuing vehicle. A generic implicit guidance function is presented to describe all known guidance laws, and a practical model with time-varying guidance parameters is used to approximate the generic implicit guidance function. Based on this model, a LPF enhanced Adaptive Kalman Filter is proposed to recognize the guidance law in real-time. Simulation results show that the proposed algorithm can recognize the guidance law fast and effectively when the non-cooperative vehicle employs either the Proportional Navigation guidance law or the Bang-Bang guidance law.