Hi-Geo-Ti: A Visual Analytic Design for Pedestrian Trajectories Using Hierarchical Geographical Timelines

ABSTRACT

With the development of computer vision technology, pedestrian trajectory tracking technology pedestrian re-recognition technology has been more and more widely used, and an explicit and accurate representation illustrating the spatial and temporal correlation of a pedestrian’s movement is the key to understanding his/her trajectory in space and time. A scalable visual analytics system called Hi-Geo-Ti is proposed that applies hierachical geographical timelines to allow its users to extract and visualize a pedestrian’s trajectory from a massive storage of images instantaneously. In particular, Hi-Geo-Ti incorporates semantic correlations produced by person re-identification with spatial and temporal attributes of the camera, based on which it creates an interactive combination of 3D trajectory map with 2D plan plot to visually resolve the spatial-temporal entanglement. Taking the transmission process of Covid-19 as case study, by combining with ReID technology, the assistance of proposed visualization system in the fight against the epidemic is demonstrated and user surveys are conducted to verify the effectiveness of proposed design. © 2022 Institute of Computing Technology. All rights reserved.