Normalcy decision in video security involves highly uncertain phenomena due to its inherited insufficient knowledge, intrinsic ambiguity in human cognition, measurement error, etc. This paper presents a hierarchical spatiotemporal trajectory modeling for dynamic trajectory analysis using sparse trajectory data. The trajectory data is assumed to be given by people detection and tracking methods, which are also challenging issues due to occlusion, noise, illumination changes, etc. The proposed method partitions the trajectory feature space into the attributes of trajectory position, direction, and speed. Inherent uncertainty of video trajectory is tackled by employing the uncertainty propagation model of a trajectory segment and Markov random field in analyzing the uncertainty attributes of object movement direction and speed. The proposed method can be used in online learning for incremental adaptation as well as offline learning for optimality guarantee. The method was evaluated using both synthetic trajectories and video streams of multiple people movements acquired from multiple video cameras developed by GE Global Research Center and KAL beta sites. Extensive experiments were performed using video sequences in real world and synthesized trajectories, which achieved very encouraging results.