Deploying unmanned aerial vehicle (UAV) networks to provide coverage for outdoor users has attracted great attention during the last decade. Terrain information requires extensive attention in outdoor UAV networks, and it is one of the most important factors affecting coverage performance. Providing tractable models and common methods is necessary to generalize the terrain-based outdoor UAV positioning strategies. In this thesis, we demonstrate that UAVs can provide stable coverage for regularly moving users based on the existing local terrain reconstruction methods with UAV sampling. Next, a coarse-grained UAV deployment can be performed with a simple set of parameters that characterize the terrain features. A stochastic geometry framework can provide general analytical results for the above coarse-grained UAV networks. In addition, the UAV can avoid building blockage without prior terrain information through real-time linear-trajectory search. We proposed four algorithms related to the combinations of collecting prior terrain information and using real-time search, and then their performances are evaluated and compared in different scenarios. By adjusting the height of the UAV based on terrain information collected before networking, the performance is significantly enhanced compared to the one when no terrain information is available. The algorithm based on real-time search further improves the coverage performance by avoiding the shadow of buildings. During the execution of the real-time search algorithm, the search distance is reduced using the collected terrain information.