Abstract
Pedestrian traffic flow estimation is essential for public place design and construction planning. Traditional data collection by human investigation is tedious, inefficient and expensive. Panoramic laser scanners, e.g. Velodyne HDL-64E, which scan surroundings repetitively at a high frequency, have been increasingly used for 3D object tracking. In this paper, a simultaneous detection and tracking (SDAT) method is proposed for precise and automatic pedestrian trajectory recovery. First, the dynamic environment is detected using two different methods, <i>Nearest-point</i> and <i>Max-distance</i>. Then, all the points on moving objects are transferred into a space-time (<i>x</i>, <i>y</i>, <i>t</i>) coordinate system. The pedestrian detection and tracking amounts to assign the points belonging to pedestrians into continuous trajectories in space-time. We formulate the point assignment task as an energy function which incorporates the point evidence, trajectory number, pedestrian shape and motion. A low energy trajectory will well explain the point observations, and have plausible trajectory trend and length. The method inherently filters out points from other moving objects and false detections. The energy function is solved by a two-step optimization process: tracklet detection in a short temporal window; and global tracklet association through the whole time span. Results demonstrate that the proposed method can automatically recover the pedestrians trajectories with accurate positions and low false detections and mismatches.
Highlights
It is common that public places, e.g. squares and concourses, need to be renovated, expanded or redesigned
Since a tracklet is only composed of two points in space-time cube, complete trajectories can be recovered for a long time-span dataset even if itself does not fit in RAM
The experimental data are acquired in Paris by a mobile mapping system (MMS) called Stereopolis (Paparoditis et al, 2012) using a HDL-64E Velodyne laser scanner, which is composed of 64 vertically distributed sensors
Summary
It is common that public places, e.g. squares and concourses, need to be renovated, expanded or redesigned. One of the main factors to be considered is the pedestrian traffic flow. Field data for the flow estimation are collected by human visual counting. We investigate the potential of using laser scanning techniques for automatic pedestrian trajectory estimation. The objective is to detect the moving pedestrians and recover their trajectories. Pedestrian, or in general, moving object detection and tracking has been studied in both computer vision and robotics for various applications, e.g. surveillance, autonomous driving. We aim for large scale long term monitoring in order to study the general moving patterns. Accurate geo-located moving patterns can be incorporated into GIS platforms for precise agent-based modelling
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
