Semantic segmentation of trajectories with agent models
This addresses trajectory segmentation for clustering and classification tasks, but appears incremental as it builds on existing methods like HMMs.
The paper tackles the problem of segmenting trajectories into meaningful parts by proposing a method that uses learned behavior models and a hidden Markov model, showing its effectiveness compared to the Ramer-Douglas-Peucker algorithm.
In many cases, such as trajectories clustering and classification, we often divide a trajectory into segments as preprocessing. In this paper, we propose a trajectory semantic segmentation method based on learned behavior models. In the proposed method, we learn some behavior models from video sequences. Next, using learned behavior models and a hidden Markov model, we segment a trajectory into semantic segments. Comparing with the Ramer-Douglas-Peucker algorithm, we show the effectiveness of the proposed method.