Classifying pedestrian trajectories by Machine learning using laser sensor data

Abstract. In the field of facility planning, the analysis of pedestrian trajectories using laser sensor-based behavior monitoring technologies is a proven way to improve our understanding of the behavioral features of foot-travelers. While these technologies can gather large volumes of trajectory data, the analysis of such data is a chaotic and complicated task and creates a large workload if it must be interpreted visually by human analysts. Hence, a method is needed for automatically extracting the features and their separate components from pedestrian trajectories and patterns. This study proposes just such a method based on a Restricted Boltzmann machine, a machine learning tool, to automatically extract and classify the latent features of pedestrian trajectories. Our method was applied to data taken in the outpatient waiting area of a hospital and the machine learning generated results were compared to those of visual classifications by human analysts. It was shown to be functional for classifying trajectories by orientation, stopping location and walking speed, and was considered effective for furnishing rough classifications resembling the intuition-based classifications of a human analyst.