The current wireless positioning technology can not adapt to complex environment and has low positioning accuracy. In order to solve the problems, a mobile terminal positioning method driven by road test data was proposed. Firstly, based on the location algorithm of base station and the description algorithm of base station signal coverage, the location-coverage model of base station base was established. By matching the initial parameters of the mobile terminal with the model base, the initial range of the mobile terminal was obtained. Secondly, the road classification database was established based on the extraction algorithm of road feature, and the wireless signal feature matching algorithm was used to match the road information of the mobile terminal. Finally, the model base of longitude-latitude and intensity mapping was established and the precise position of the mobile terminal was determined by using the terminal signal comparison algorithm. The theoretical analysis and experimental results show that the probability of 2 m localization accuracy of the base station reaches 60%, the probability of 3 m reaches 77%, which are improved respectively by about 39% and 12% than those before whitening, and the description algorithm of base station signal coverage can also describe the coverage of base station signal more accurately. The accuracy improvement of the two parts can improve the final positioning accuracy.