Abstract: Vehicle recognition is one of the most important parts of intelligent transportation system. In addition, it is also the basis of other high-level intelligent tasks such as traffic management, self-driving, suspect tracing and behavior analysis. Firstly the difficulties and challenges in vehicle recognition researches were presented in this paper. On the basis of this, a detailed summary in the advanced technology development of vehicle recognition researches of shallow learning and deep learning was given. Finally the problems be solved were analyzed, and the future research direction in vehicle recognition researches field was proposed.