The vehicle identification is a key technology of vehicle automatic driving and assistance systems. This paper proposes a new fast vehicle detection method based on feature learning and real-time prediction by combining ARMA model and AdaBoost algorithm, which can be applied in car driver assistance systems for road detection and vehicle identification with a monocular camera. Experimental results show that our proposed algorithm can take the target's prior information into account, and extend AdaBoost algorithm in the time dimension that improve the accuracy of real-time detection to be faster and more accurate than the existing methods.