With the development of urbanization, the number of cars was proliferating fast. Urban transportation provides convenience for city resident, meanwhile, it also brings many challenges, such as causing a difficulty for taking a taxi. To solve the problem, main work was composed of two parts: first, a method was proposed to estimate the probability and waiting time for a vacant taxi at a given time and place, second, an recommendations was provided for passengers of where to wait for a taxi. In order to complete the main work, the Large-scale Taxi GPS Traces was preprocessed and the road characteristic index was generated. Then NPP (Nonhomogeneous Poisson Process) was used to predict and recommend. Compared with other related advanced methods, the results show that the method has more advantages in accuracy and efficiency.