Realistic modeling of the movement of people in an environment is critical for evaluating the performance of mobile wireless systems such as urban sensing or mobile sensor networks. Existing human movement models are either fully synthetic or rely on traces of actual human movement. There are many situations where we cannot perform an accurate simulation without taking into account what the people are actually doing. For instance, in theme parks, the movement of people is strongly tied to the locations of the attractions and is synchronized with major external events. For these situations, we need to develop scenario specific models. In this paper, we present a model of the movement of visitors in a theme park. The nondeterministic behavior of the human walking pattern is combined with the deterministic behavior of attractions in the theme park. The attractions are divided into groups of rides, restaurants and live shows. The time spent by visitors at different attractions is calculated using specialized queuing-theoretic models. We compare the realism of the model by comparing its simulations to the statistics of the theme parks and to real-world GPS traces of visitor movement. We found that our model provides a better match to the real-world data compared to current state-of-the-art movement models.